Search

This paper presents the overview and rationale behind the Decoder-Side Depth Estimation (DSDE) mode of the MPEG Immersive Video (MIV) standard, using the Geometry Absent profile, for efficient compression of immersive multiview video. A MIV bitstream generated by an encoder operating in the DSDE mode does not include depth maps. It only contains the information required to reconstruct them in the client or in the cloud: decoded views and metadata. The paper explains the technical details and techniques supported by this novel MIV DSDE mode. The description additionally includes the specification on Geometry Assistance Supplemental Enhancement Information which helps to reduce the complexity of depth estimation, when performed in the cloud or at the decoder side. The depth estimation in MIV is a non-normative part of the decoding process, therefore, any method can be used to compute the depth maps. This paper lists a set of requirements for depth estimation, induced by the specific characteristics of the DSDE. The depth estimation reference software, continuously and collaboratively developed with MIV to meet these requirements, is presented in this paper. Several original experimental results are presented. The efficiency of the DSDE is compared to two MIV profiles. The combined non-transmission of depth maps and efficient coding of textures enabled by the DSDE leads to efficient compression and rendering quality improvement compared to the usual encoder-side depth estimation. Moreover, results of the first evaluation of state-of-the-art multiview depth estimators in the DSDE context, including machine learning techniques, are presented. [ABSTRACT FROM AUTHOR]

Crowd counting is a task of intelligent applications, and its operation efficiency is very important. However, in order to obtain a better counting performance, most of the existing works often design larger and more complex network structures, which will result in them occupying considerable memory, time and other resources at runtime, seriously limiting their deployment scope and making it difficult to be widely used in practical scenarios. In this paper, in order to overcome the above problems, we propose an effective lightweight encoding-decoding crowd counting network, named Lw-Count. Specifically, in the encoding process, we design an efficient and lightweight convolution module (ELCM), which extracts the crowd features in the network through a refined ghost block to reduce the network parameters and computing cost, and solves the problem of inaccurate counting caused by uneven crowd distribution through spatial group normalization (SGN). In the decoding process, we design a scale regression module (SRM) to reduce the error details and chessboard effect caused by linear interpolation and deconvolution. In addition, we design a new loss function, which enhances the spatial correlation of the density map and the sensitivity of the crowd through a regional normalized cross-correlation loss and counting loss, to ensure the counting accuracy. Extensive experiments on five mainstream datasets demonstrate that Lw-Count achieves an optimal trade-off between counting performance and running speed compared with other methods. [ABSTRACT FROM AUTHOR]

Transform plays a crucial role in video coding, since it is in the transform domain that the bitrate reduction happens. Recently, coding with transform competition has emerged, especially inside the ITU-T and ISO/MPEG Joint Video Exploration Team, where the adaptive multiple transforms have been thoroughly tested. In this paper, it is proposed to investigate the design of transform competition systems for the purpose of inter-predicted residuals. Several systems are proposed and evaluated in terms of coding efficiency, storage requirement, and encoding complexity. A first approach selects the best transform for a residual block in a pre-established list of transforms. An extended version is also considered, where the number of transforms varies within an image area. Experimental results show that the proposed designs achieve significant bitrate savings over high efficiency video coding from −0.2% to −1.4%. [ABSTRACT FROM AUTHOR]

Recently, multiple ($k, n$) region-incrementing VCSs (RIVCSs) have been proposed that can gradually reconstruct secrets in a single image. In ($k, n$)-RIVCS, the secret image is subdivided into multiple regions in such a way that any $t$ shadow images, where $k \le t \le n$ , can be used to reveal the secret in the ($t-k+1$)th region. This region-incrementing property provides progressive decoding. However, the regions in previous RIVCSs are disjointed: no two regions have overlapping areas. In this paper, we discuss a ($k, n$) region-in-region progressive VCS (RPVCS). Our ($k, n$)-RPVCS has ($n-k+1$) secrecy-level regions, and each region can be located within any previous region. This new type of region allocation not only provides more areas in which to hide the secret compared with the non-overlapping regions in RIVCS but also provides different presentation methods in progressive decoding. [ABSTRACT FROM AUTHOR]

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high segmentation accuracy. However, they usually adopt the feature alignment modules with the same network configuration in the decoder and thus ignore the different roles of stages of the decoder during feature aggregation, leading to a complex decoder structure. Such a manner greatly affects the inference speed. In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes. Specifically, a Stage-aware Feature Alignment module (SFA) is proposed to align and aggregate two adjacent levels of feature maps effectively. In the SFA, by taking into account the unique role of each stage in the decoder, a novel stage-aware Feature Enhancement Block (FEB) is designed to enhance spatial details and contextual information of feature maps from the encoder. In this way, we are able to address the misalignment problem with a very simple and efficient multi-branch decoder structure. Moreover, an auxiliary training strategy is developed to explicitly alleviate the multi-scale object problem without bringing additional computational costs during the inference phase. Experimental results show that the proposed SFANet exhibits a good balance between accuracy and speed for real-time semantic segmentation of street scenes. In particular, based on ResNet-18, SFANet respectively obtains 78.1% and 74.7% mean of class-wise Intersection-over-Union (mIoU) at inference speeds of 37 FPS and 96 FPS on the challenging Cityscapes and CamVid test datasets by using only a single GTX 1080Ti GPU. [ABSTRACT FROM AUTHOR]

Along with the rapid increase in the availability of high-quality video formats such as high definition (HD), ultra HD, and high dynamic range, a huge demand for data rates during their transmission has become inevitable. Consequently, the role of video compression techniques has become crucially important in the process of mitigating the data rate requirements. Even though the latest video codec high efficiency video coding (HEVC) has succeeded in significantly reducing the data rate compared to its immediate predecessor H.264/advanced video coding, the HEVC coded videos in the meantime have become even more vulnerable to network impairments. Therefore, it is equally important to assess the consumers’ perceived quality degradation prior to transmitting HEVC coded videos over an error-prone network, and to include error resilient features so as to minimize the adverse effects of those impairments. To this end, this paper proposes a probabilistic model which accurately predicts the overall distortion of the decoded video at the encoder followed by an accurate QP– $\lambda $ relationship which can be used in the rate-distortion optimization (RDO) process. During the derivation process of the probabilistic model, the impacts from the motion vectors, the pixels in the reference frames, and the clipping operations are accounted, and consequently, the model is capable of minimizing the prediction error to as low as 3.11%, whereas the state-of-the-art methods cannot reach below 20.08%, under identical conditions. Furthermore, the enhanced RDO process has resulted in 21.41%–43.59% improvement in the BD-rate compared to the state-of-the-art error resilient algorithms. [ABSTRACT FROM AUTHOR]

Transform, as one of the most important modules of mainstream video coding systems, seems very stable over the past several decades. However, recent developments indicate that bringing more options for transform can lead to coding efficiency benefits. In this paper, we go further to investigate how the coding efficiency can be improved over the state-of-the-art method by adapting a transform for each block. We present a variable block-sized signal-dependent transforms (SDTs) design based on the High Efficiency Video Coding (HEVC) framework. For a coding block ranged from $4\times4$ to $32\times32$ , we collect a quantity of similar blocks from the reconstructed area and use them to derive the Karhunen–Loève transform. We avoid sending overhead bits to denote the transform by performing the same procedure at the decoder. In this way, the transform for every block is tailored according to its statistics, to be signal-dependent. To make the large block-sized SDTs feasible, we present a fast algorithm for transform derivation. Experimental results show the effectiveness of the SDTs for different block sizes, which leads to up to 23.3% bit-saving. On average, we achieve BD-rate saving of 2.2%, 2.4%, 3.3%, and 7.1% under AI-Main10, RA-Main10, RA-Main10, and LP-Main10 configurations, respectively, compared with the test model HM-12 of HEVC. The proposed scheme has also been adopted into the joint exploration test model for the exploration of potential future video coding standard. [ABSTRACT FROM AUTHOR]

Prevalent video codec implementations deployed in the field often solely support chrominance sub-sampled video data represented by the YCbCr 4:2:0 format. For certain applications like screen sharing, however, chroma sub-sampling leads to disturbing artifacts, especially for text or graphics with thin lines. It is desirable to reduce these artifacts while maintaining compatibility with all user devices. For this reason, an enhancement layer coding framework for chroma-format scalable coding with specific focus on screen content is proposed in this paper. Based on an analysis of screen content data characteristics, the enhancement layer codec is optimized specifically for this content class, is of low algorithmic complexity, and applicable with any image or video codec for base layer compression in a joint coding system. The system is intentionally not designed as a general purpose lossless YCbCr 4:4:4 coding scheme, but instead chooses to close a quality gap that prevalent video codecs do not address. Experimental analysis reveals an average BD-PSNR gain in the RGB domain of 1.0 dB comparing the proposed two-layer scalable coding approach to single layer compression using base layer coding only. In relation to simulcast coding, an average BDR RGB difference of 8.1% is observed. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the technologies for in-loop processing and filtering in the Versatile Video Coding (VVC) standard. These processes comprise luma mapping with chroma scaling, deblocking filter, sample adaptive offset, adaptive loop filter and cross-component adaptive loop filter. They are qualified as “in-loop” because they are applied inside the encoding and decoding loops, before storing the pictures in the decoded picture buffer. The filters are complementary and address different purposes. Luma mapping with chroma scaling aims at adaptively modifying the coded samples distribution for improved coding efficiency. The deblocking filter aims at reducing blocking discontinuities. Sample adaptive offset mostly aims at reducing artifacts resulting from the quantization of transform coefficients. Adaptive loop filter and cross-component adaptive loop filter are adaptive filters enabling to enhance the reconstructed signal, using for instance Wiener-filter encoding approaches. The paper provides an overview of the in-loop filtering process and a detailed description of the filtering algorithms. Objective compression efficiency results are provided for each filter, with indication of cumulative coding gains. Subjective benefits are illustrated. Implementation issues considered during the design of the VVC in-loop filters are also discussed. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the geometric partitioning mode (GPM) algorithm that is a part of the most recent Versatile Video Coding (VVC) standard. The GPM algorithm aims to increase the partitioning precision of moving objects using non-rectangular and asymmetric rectangular partitions on top of the conventional rectangular block partitioning structure of VVC. Novel features of GPM contributing to the increase in coding efficiency and the reduction in encoder and decoder complexity are detailed and analyzed in this paper. Evaluated with VVC test model version 8.0 under the joint video experts team common test conditions, experimental results show that the presented GPM algorithm provides luma Bjøntegaard Delta rate reduction of 0.70% for random access and of 1.55% for low delay with B slices configurations, with roughly 3% to 5% additional encoding time and negligible decoder runtime change. Furthermore, as GPM provides more precise partitions for the boundaries of the moving objects, an improvement of visual quality is seen in GPM coded sequences. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the decoder-side motion vector refinement (DMVR) algorithm in the Versatile Video Coding (VVC) standard. The proposed DMVR algorithm aims to increase the prediction accuracy of the blocks coded in merge mode using the bilateral matching-based refinement method. Compared with previous decoder-side motion vector derivation approaches, the proposed method significantly increases the coding efficiency without signaling additional side information. Furthermore, the hardware implementation considerations of the DMVR design are particularly focused in this study. This paper details and analyzes the novel features of DMVR contributing to the increase in coding efficiency and the reduction in computational complexity and implementation difficulty. Experimental results based on the VVC test model version 8.0 demonstrate that average Bjøntegaard Delta rate savings of 0.80 % and 2.81 % are achieved for the “tool-off” and “tool-on” test configurations, respectively. Moreover, 4 % additional decoding time and negligible additional external memory bandwidth requirements of DMVR based on the common test conditions for VVC are reported. [ABSTRACT FROM AUTHOR]

Tile-based viewport-adaptive streaming methods have been used in delivering omnidirectional video for virtual reality applications. In these methods, the 360° video is encoded in multiple quality versions by using the motion constrained tile set (MCTS) technique. A set of high-quality and low-quality tiles, corresponding to viewport and non-viewport areas, respectively, are selected and transmitted to the user. However, these methods require frequent intra random access points to ensure seamless viewport switching capability, very high decoding complexity, or a multi-layer coding scheme. The frequent intra random access points include very high bitrate in viewport switching points. The high decoding complexity and multi-layer decoder requirements are not aligned with the omnidirectional media format (OMAF) standard. Such requirements make these methods sub-optimal or impractical for streaming the omnidirectional video. This paper studies the current tile-based solutions for delivering the omnidirectional content. Moreover, the OMAF-compliant shared coded picture (SCP)-based scheme is proposed in this paper for streaming the omnidirectional video. The core concept of the SCP-based method is to manipulate the switching point pictures in a way that the frequent intra-coded pictures are no longer required for the viewport switching operations between different quality versions of the content. The experiments illustrated that the SCP-based method outperforms the MCTS-based method on average by 11% to 14% in terms of streaming bitrate reduction with only 4% extra decoding complexity. [ABSTRACT FROM AUTHOR]

Image recapture is one of the simplest methods of content leakage, but is very difficult to address with the rapid development and dissemination of digital devices. This paper proposes novel secure display schemes to prevent image recapture on a polarized 3D system without additional hardware. Using commercial polarized 3D characteristics, the secret image to be protected from recapturing is encrypted on a pixel-by-pixel basis and decrypted with polarized glasses (PGs). Moreover, the proposed secure display schemes allow for the restricted viewing of secret images that only authorized people may see or the selective viewing of secret images and public images that anyone may see. Quantitative and qualitative analyses of the experimental results show that the proposed schemes can prevent content leakage from recaptured still or time axis images via a digital camera because the secret image is statistically encrypted, similar to random noise. As such, the restricted viewing or the selective viewing is possible depending on the presence of PGs. Therefore, the proposed schemes not only prevent image recapture using digital devices but also implement a secure display using PGs. [ABSTRACT FROM AUTHOR]

This paper proposes a novel functionality in wavelet-based irregular mesh coding, which is interactive region-of-interest (ROI) support. The proposed approach enables the user to define the arbitrary ROIs at the decoder side and to prioritize and decode these regions at arbitrarily high-granularity levels. In this context, a novel adaptive wavelet transform for irregular meshes is proposed, which enables: 1) varying the resolution across the surface at arbitrarily fine-granularity levels and 2) dynamic tiling, which adapts the tile sizes to the local sampling densities at each resolution level. The proposed tiling approach enables a rate-distortion-optimal distribution of rate across spatial regions. When limiting the highest resolution ROI to the visible regions, the fine granularity of the proposed adaptive wavelet transform reduces the required amount of graphics memory by up to 50%. Furthermore, the required graphics memory for an arbitrary small ROI becomes negligible compared to rendering without ROI support, independent of any tiling decisions. Random access is provided by a novel dynamic tiling approach, which proves to be particularly beneficial for large models of over 106 ~ 107 vertices. The experiments show that the dynamic tiling introduces a limited lossless rate penalty compared to an equivalent codec without ROI support. Additionally, rate savings up to 85% are observed while decoding ROIs of tens of thousands of vertices. [ABSTRACT FROM AUTHOR]

Visual question generation task aims to generate meaningful questions about an image targeting an answer. Existing methods focus on the visual concepts in the image for question generation. However, humans inevitably use their knowledge related to visual objects in images to construct questions. In this paper, we propose a knowledge-based visual question generation model that can integrate visual concepts and non-visual knowledge to generate questions. To obtain visual concepts, we utilize a pre-trained object detection model to obtain object-level features of each object in the image. To obtain useful non-visual knowledge, we first retrieve the knowledge from the knowledge-base related to the visual objects in the image. Considering that not all retrieved knowledge is helpful for this task, we introduce an answer-aware module to capture the candidate knowledge related to the answer from the retrieved knowledge, which ensures that the generated content can be targeted at the answer. Finally, object-level representations containing visual concepts and non-visual knowledge are sent to a decoder module to generate questions. Extensive experiments on the FVQA and KBVQA datasets show that the proposed model outperforms the state-of-the-art models. [ABSTRACT FROM AUTHOR]

The critical challenge of single image inpainting stems from accurate semantic inference via limited information while maintaining image quality. Typical methods for semantic image inpainting train an encoder-decoder network by learning a one-to-one mapping from the corrupted image to the inpainted version. While such methods perform well on images with small corrupted regions, it is challenging for these methods to deal with images with large corrupted area due to two potential limitations. 1) Such one-to-one mapping paradigm tends to overfit each single training pair of images; 2) The inter-image prior knowledge about the general distribution patterns of visual semantics, which can be transferred across images sharing similar semantics, is not explicitly exploited. In this paper, we propose the Generative Memory-guided Semantic Reasoning Model (GM-SRM), which infers the content of corrupted regions based on not only the known regions of the corrupted image, but also the learned inter-image reasoning priors characterizing the generalizable semantic distribution patterns between similar images. In particular, the proposed GM-SRM first pre-learns a generative memory from the whole training data to explicitly learn the distribution of different semantic patterns. Then the learned memory are leveraged to retrieve the matching semantics for the current corrupted image to perform semantic reasoning during image inpainting. While the encoder-decoder network is used for guaranteeing the pixel-level content consistency, our generative priors are favorable for performing high-level semantic reasoning, which is particularly effective for inferring semantic content for large corrupted area. Extensive experiments on Paris Street View, CelebA-HQ, and Places2 benchmarks demonstrate that our GM-SRM outperforms the state-of-the-art methods for image inpainting in terms of both visual quality and quantitative metrics. [ABSTRACT FROM AUTHOR]

Image captioning has made significant achievement through developing feature extractor and model architecture. Recently, the image region features extracted by object detector prevail in most existing models. However, region features are criticized for the lacking of background and full contextual information. This problem can be remedied by providing some complementary visual information from patch features. In this paper, we propose a Double-Stream Position Learning Transformer Network (DSPLTN) which exploits the advantages of region features and patch features. Specifically, the region-stream encoder utilizes a Transformer encoder with Relative Position Learning (RPL) module to enhance the representations of region features through modeling the relationships between regions and positions respectively. As for the patch-stream encoder, we introduce convolutional neural network into the vanilla Transformer encoder and propose a novel Convolutional Position Learning (CPL) module to encode the position relationships between patches. CPL improves the ability of relationship modeling by combining the position and visual content of patches. Incorporating CPL into the Transformer encoder can synthesize the benefits of convolution in local relation modeling and self-attention in global feature fusion, thereby compensating for the information loss caused by the flattening operation of 2D feature maps to 1D patches. Furthermore, an Adaptive Fusion Attention (AFA) mechanism is proposed to balance the contribution of enhanced region and patch features. Extensive experiments on MSCOCO demonstrate the effectiveness of the double-stream encoder and CPL, and show the superior performance of DSPLTN. [ABSTRACT FROM AUTHOR]

RGB-D Salient Object Detection (RGB-D SOD) aims at detecting remarkable objects by complementary information from RGB images and depth cues. Although many outstanding prior arts have been proposed for RGB-D SOD, most of them focus on performance enhancement, while lacking concern about practical deployment on mobile devices. In this paper, we propose mobile asymmetric dual-stream networks (MoADNet) for real-time and lightweight RGB-D SOD. First, inspired by the intrinsic discrepancy between RGB and depth modalities, we observe that depth maps can be represented by fewer channels than RGB images. Thus, we design asymmetric dual-stream encoders based on MobileNetV3. Second, we develop an inverted bottleneck cross-modality fusion (IBCMF) module to fuse multimodality features, which adopts an inverted bottleneck structure to compensate for the information loss in the lightweight backbones. Third, we present an adaptive atrous spatial pyramid (A2SP) module to speed up the inference, while maintaining the performance by appropriately selecting multiscale features in the decoder. Extensive experiments are conducted to compare our method with 15 state-of-the-art approaches. Our MoADNet obtains competitive results on five benchmark datasets under four evaluation metrics. For efficiency analysis, the proposed method significantly outperforms other baselines by a large margin. The MoADNet only contains 5.03 M parameters and runs 80 FPS when testing a $256\times 256$ image on a single NVIDIA 2080Ti GPU. [ABSTRACT FROM AUTHOR]

This paper presents an advanced depth intra-coding approach for 3D video coding based on the High Efficiency Video Coding (HEVC) standard and the multiview video plus depth (MVD) representation. This paper is motivated by the fact that depth signals have specific characteristics that differ from those of natural signals, i.e., camera-view video. Our approach replaces conventional intra-picture coding for the depth component, targeting a consistent and efficient support of 3D video applications that utilize depth maps or polygon meshes or both, with a high depth coding efficiency in terms of minimal artifacts in rendered views and meshes with a minimal number of triangles for a given bit rate. For this purpose, we introduce intra-picture prediction modes based on geometric primitives along with a residual coding method in the spatial domain, substituting conventional intra-prediction modes and transform coding, respectively. The results show that our solution achieves the same quality of rendered or synthesized views with about the same bit rate as MVD coding with the 3D video extension of HEVC (3D-HEVC) for high-quality depth maps and with about 8% less overall bit rate as with 3D-HEVC without related depth tools. At the same time, the combination of 3D video with 3D computer graphics content is substantially simplified, as the geometry-based depth intra signals can be represented as a surface mesh with about 85% less triangles, generated directly in the decoding process as an alternative decoder output. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is the theory and practice of sub-Nyquist sampling of sparse signals of interest. Exact reconstruction may then be possible with much fewer than the Nyquist-required number of data. In this paper, we consider a multiview video system in which multiple cameras at different locations perform independent CS to simultaneously capture different views of a scene. At the decoder, we propose a disparity- and motion-compensated total variation minimization algorithm to jointly reconstruct the multiview video sequence. The experimental results show that the proposed joint reconstruction algorithm successfully exploits simultaneously intra-frame, inter-frame, and inter-view sparsity and significantly outperforms existing independent-view reconstruction, residue-view reconstruction, and motion-adaptive reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Adaptive HTTP streaming requires a video to be encoded at multiple representations, that is, different qualities. Encoding these multiple representations is a computationally complex process, especially when using the recent High Efficiency Video Coding (HEVC) standard. In this paper, we consider a multi-rate HEVC encoder and identify four types of encoding information that can be reused from a high-quality reference encoding to speed up lower quality-dependent encodings. We show that the encoding decisions from the reference cannot be directly reused, as this would harm the overall rate-distortion (RD) performance. Thus, we propose methods to use the encoding information to constrain the RD optimization of the dependent encodings so that the encoding complexity is reduced while the RD performance is kept high. We additionally show that the proposed methods can be combined, leading to an efficient multi-rate encoder that exhibits high RD performance and substantial complexity reduction. Results show that the encoding time for 12 representations at different spatial resolutions and signal qualities can be reduced on average by 38%, while the average bitrate increases by less than 1%. [ABSTRACT FROM PUBLISHER]

A block-composed background reference method is proposed in this paper for High Efficiency Video Coding (HEVC). For a group of picture (GoP), the first reconstructed picture is served as an initial background reference, which probably includes foreground content. In the subsequent coding, some background coding tree units (CTUs) in every picture are selected to be compressed with high quality. These reconstructed CTUs are used to update the background reference as well as replace the foreground content. Finally, a high-quality background reference is generated to better exploit the long-term temporal correlation in the video. There are three key technical contributions in the proposed coding scheme. First, the background reference is generated gradually by block updating instead of picture updating, which makes the scheme free of bit-rate burst and more suitable for real-time applications and can generate high-quality background reference even with complicated foreground. Second, we propose an approach to select background CTUs by taking both temporal and spatial smoothness into account. Third, we propose a model to decide the coding parameters of the selected background CTUs based on the overall picture activity, which essentially pursues the GoP-level optimal performance when making CTU-level decision. The proposed background reference is implemented into HEVC, and the experimental results demonstrate a significant improvement in coding efficiency. Compared with HEVC, our method can averagely save 14% bits in surveillance and conferencing sequences with negligible increase of encoding and decoding complexity. In particular, it can still averagely save 7.3% bits in HEVC general test sequences. Obviously, the proposed scheme can be applied to more general video contents. [ABSTRACT FROM PUBLISHER]

Unsupervised domain adaptation crowd counting (UDACC) has been studied with practical research utility by getting rid of the labeling burden on large-scale dense crowds in the target domain. Current methods generalize well within the specific domain gap by directly aligning domain distributions or translating synthetic data to realistic images. However, it is difficult to define domain gaps among complex real-world datasets, in which the images vary greatly in style, density level and/or content. To tackle this problem, in this paper, we propose a Cross-Domain Attention Network (CDANet), which can effectively generalize the model to the unlabeled domain on both unsupervised synthetic-to-realistic and realistic-to-realistic crowd counting. Specifically, we propose a Cross-Domain Attention Module (CDAM) to learn domain-related information between the source and target domain, which extracts relations in cross-domain attentive information, thus enhancing crowd-informative features. Moreover, to make our CDAM invariant to domain shifts, we introduce a consistency penalty to ensure that the attention maps are consistent before and after the domain shifting. Thus our CDANet can pay attention to the shared counting information across domains, while remaining its invariant ability during domain adaptation. Extensive experiments on several common benchmarks for UDACC demonstrate that our CDANet gets competitive results on both unsupervised synthetic-to-realistic and realistic-to-realistic UDACC tasks. [ABSTRACT FROM AUTHOR]

Image captioning generates descriptions in a natural language for a given image. Due to its great potential for a wide range of applications, many deep learning based-methods have been proposed. The co-occurrence of words such as mouse and keyboard, constitutes commonsense knowledge, which is referred to as consensus. However, it is challenging to consider commonsense knowledge in producing captions that have rich, natural, and meaningful semantics. In this paper, a Vision-enhanced and Consensus-aware Transformer (VCT) is proposed to exploit both visual information and consensus knowledge for image captioning with three key components: a vision-enhanced encoder, consensus-aware knowledge representation generator, and consensus-aware decoder. The vision-enhanced encoder extends the vanilla self-attention module with a memory-based attention module and a visual perception module for learning better visual representation of an image. Specifically, the relationships between regions in an image and the image’s global context are leveraged with scene memory in the memory-based attention module. The visual perception module further enhances the correlation among neighboring tokens in both the spatial and channel-wise dimensions. To learn consensus-aware representations, a word correlation graph is constructed by computing the statistical co-occurrence between semantic concepts. Then consensus knowledge can be acquired using a graph convolutional network in the consensus-aware knowledge representation generator. Finally, such consensus knowledge is integrated into the consensus-aware decoder through consensus memory and a knowledge-based control module to produce a caption. Experimental results on two popular benchmark datasets (MSCOCO and Flickr30k) demonstrate that our proposed model achieves state-of-the-art performance. Extensive ablation studies also validate the effectiveness of each component. [ABSTRACT FROM AUTHOR]

Category-level 6D object pose estimation has gained popularity and it is still challenging due to the diversity of different instances within the same category. In this paper, a novel category-level 6D object pose estimation framework with structure encoder and reasoning attention is proposed. A structure autoencoder is introduced to mine the shared structure features in the color images within the same category, via a distinct learning strategy that recovers the image of another instance but with the most similar pose to the input. On this basis, a reasoning attention decoder and full connected layers are stacked to form a rotation prediction network, where the structure features and 3D shape features are integrated and projected to a semantic space. The semantic space includes observed patterns and learnable patterns, which are better learned by adding a shortcut connection branch parallel to reasoning attention decoder with gradient decouple. Further reasoning based on these patterns endows the decoder with powerful feature representation. Without 3D object models, the proposed method models the attributes of category implicitly in the semantic space and better performance of 6D object pose estimation is guaranteed by reasoning on this space. The effectiveness of the proposed method is verified by the results on public datasets and actual experiments. [ABSTRACT FROM AUTHOR]

Video captioning is a joint task of computer vision and natural language processing, which aims to describe the video content using several natural language sentences. Nowadays, most methods cast this task as a mapping problem, which learns a mapping from visual features to natural language and generates captions directly from videos. However, the underlying challenge of video captioning, i.e., sequence to sequence mapping across the different domains, is still not well handled. To address these problems, we introduce the polishing mechanism in an attempt to mimic human polishing process and propose a generate-and-polish framework for video captioning. In this paper, we propose a two-step transformer based polishing network (TSTPN) consisting of two sub-modules: the generation-module is to generate the caption candidate and the polishing-module is to gradually refine the generated candidate. Specifically, the candidate provides a global information of the visual contents in a semantically-meaningful order, where it is firstly considered as a semantic intersnubber to bridge the semantic gap between the text and video, with the cross-modal attention mechanism for better cross-modal modeling; and it secondly provides a global planning ability to maintain the semantic consistency and fluency of the whole sentence for better sequence mapping. In experiments, we present adequate evaluations to show that the proposed TSTPN achieves the comparable and even better performance than the state-of-the-art methods on the benchmark datasets. [ABSTRACT FROM AUTHOR]

With the widespread use of deep learning in single object tracking task, mainstream tracking algorithms treat tracking as a combined classification and regression problem. Classification aims at locating an arbitrary target, and regression aims at estimating the corresponding bounding box. In this paper, we focus on regression and propose a novel box estimation network, which consists of a transformer encoder target pyramid guide (TPG) and transformer decoder target pyramid spread (TPS). Specifically, the transformer encoder TPG is designed to generate fine-grained prior knowledge with explicit representation for template targets. In contrast to the raw transformer encoder, we capture the visual dependence through local-global self-attention and deem the multi-scale target regions as the “local” region. Using this fine-grained prior knowledge, we design the transformer decoder TPS to spread it to the subsequent search regions with high affinity to accurately estimate the bounding boxes. Considering that self-attention fails to model information interaction across channels between the template target and search regions, we develop a channel-wise cross-attention block within the TPS as compensation. Extensive experiments on the OTB100, UAV123, NFS, VOT2020, VOT2021, LaSOT, LaSOT_ext, TrackingNet and GOT-10k benchmarks show that the proposed box estimation network outperforms most existing box estimation methods. Furthermore, our trackers based on this estimation network exhibit a competitive performance against state-of-the-art trackers. [ABSTRACT FROM AUTHOR]

Recent years have witnessed the exponential increase in the demand for ultra high definition (UHD) video compression. The third generation of Audio Video Coding Standard (AVS3), which is also known as IEEE Standard 1857.10, is the latest audio and video coding standard developed by the China AVS working group. In AVS3, targeting for UHD videos, a series of efficient coding tools have been introduced, leading to the dramatical increase of computational burden. In this scenario, real-time decoding of UHD videos becomes extremely challenging. This paper presents an improved hybrid CPU + GPU accelerated framework for AVS3 decoding. In particular, the motion vector (MV) derivation process is extracted from entropy decoding threads on the CPU. Therefore, the dependency between threads is removed and the entropy decoding can be performed by multiple threads efficiently. Regarding the GPU, we design compact data structures for transform, prediction, and in-loop filtering to reduce the burden of data transmission. A flexible information buffer supporting multi-thread random writing is further created to coordinate the computation between CPU and GPU. Through asynchronous operations on the buffer, the computation of different computing units and the data transmission between them could be performed in parallel. With NVIDIA GeForce RTX 2080Ti GPU and Intel Core i7 8700K CPU, the proposed decoder achieves 151 frames per second (fps) for 4K videos and 55 fps for 8K videos in all intra configuration. In random access configuration, 218 fps and 74 fps are obtained for 4K and 8K videos, respectively. [ABSTRACT FROM AUTHOR]

Single instruction multiple data (SIMD) instructions have been commonly used to accelerate video codecs. The recently introduced High Efficiency Video Coding (HEVC) codec like its predecessors is based on the hybrid video codec principle and, therefore, is also well suited to be accelerated with SIMD. In this paper we present the SIMD optimization for the entire HEVC decoder for all major SIMD instruction set architectures. Evaluation has been performed on 14 mobile and PC platforms covering most major architectures released in recent years. With SIMD, up to $5\times $ speedup can be achieved over the entire HEVC decoder, resulting in up to 133 and 37.8 frames/s on average on a single core for Main profile 1080p and Main10 profile 2160p sequences, respectively. [ABSTRACT FROM AUTHOR]

Most of the advances in video coding technology focus on applications that require low bitrates, for example, for content distribution on a mass scale. For these applications, the performance of conventional coding methods is typically sufficient. Such schemes inevitably introduce large losses to the signal, which are unacceptable for numerous other professional applications such as capture, production, and archiving. To boost the performance of video codecs for high-quality content, better techniques are needed especially in the context of the prediction module. An analysis of conventional intra prediction methods used in the state-of-the-art High Efficiency Video Coding (HEVC) standard is reported in this paper, in terms of the prediction performance of such methods in the frequency domain. Appropriately modified encoder and decoder schemes are presented and used for this paper. The analysis shows that conventional intra prediction methods can be improved, especially for high frequency components of the signal which are typically difficult to predict. A novel approach to improve the efficiency of high-quality video coding is also presented in this paper based on such analysis. The modified encoder scheme allows for an additional stage of processing performed on the transformed prediction to replace selected frequency components of the signal with specifically defined synthetic content. The content is introduced in the signal using feature-dependent lookup tables. The approach is shown to achieve consistent gains against conventional HEVC with up to −5.2% coding gains in terms of bitrate savings. [ABSTRACT FROM AUTHOR]

In practical multimedia systems, the content of coded video streams often needs to be re-edited at the nodes of transmitting networks. For example, logo insertion is always required for copyright protection at different local transmitting nodes. This kind of video stream editing is denoted as video content editing transcoding (VCET) in this paper. Though some techniques have been suggested for VCET, these methods cannot meet the requirement of dynamic transmitting bandwidth in practical applications. In this paper, we proposed an interface macroblock-based transcoding scheme for VCET, which can reuse the variable length codes of the original video streams as much as possible to achieve the best VCET quality. In order to ensure that the edited video streams can be transmitted by the original bandwidth, we also proposed a rate control algorithm for VCET, which can accurately control the bitrate of edited video streams according to the frame level coding bits of the original video streams. Experimental results showed that the proposed scheme achieved substantially better results in bitrate accuracy, computational complexities, and video quality than many other existing schemes. [ABSTRACT FROM PUBLISHER]

Video coding in the YCbCr color space has been widely used, since it is efficient for compression, but it can result in color distortion due to conversion error. Meanwhile, coding in the RGB color space maintains high color fidelity, having the drawback of a substantial bitrate increase with respect to YCbCr coding. Cross-component prediction (CCP) efficiently compresses video content by decorrelating color components while keeping high color fidelity. In this scheme, the chroma residual signal is predicted from the luma residual signal inside the coding loop. This paper gives a description of the CCP scheme from several points of view, from theoretical background to practical implementation. The proposed CCP scheme has been evaluated in standardization communities and adopted into H.265/High Efficiency Video Coding (HEVC) Range Extensions. The experimental results show significant coding performance improvements for both natural and screen content video, while the quality of all color components is maintained. The average coding gains for natural video are 17% and 5% bitrate reduction in the case of intra coding and 11% and 4% in the case of inter coding for RGB and YCbCr coding, respectively, while the average increment of encoding and decoding times in the HEVC reference software implementation are 10% and 4%, respectively. [ABSTRACT FROM AUTHOR]

This paper presents methods based on convolutional neural networks (CNNs) for removing compression artifacts. We modify the Inception module for the image restoration problem and use it as a building block for constructing blind and non-blind artifact removal networks. It is known that a CNN trained in a non-blind scenario (known compression quality factor) performs better than the one trained in a blind scenario (unknown factor), and our network is not an exception. However, the blind system is more practical because the compression quality factor is not always available or does not reflect the actual quality when the image is a transcoded or requantized image. Hence, in this paper, we also propose a pseudo-blind system that estimates the quality factor for a given compressed image and then applies a network that is trained with a similar quality factor. For this purpose, we propose a CNN that estimates the compression quality factor and prepare several non-blind artifact removal networks that are trained for some specific compression quality factors. We train the networks and conduct experiments on widely used compression standards, such as JPEG, MPEG-2, H.264, and HEVC. In addition, we conduct experiments for dynamically changing and transcoded videos to demonstrate the effectiveness of the quality estimation method. The experimental results show that the proposed pseudo-blind network performs better than the blind one for the various cases stated above and requires fewer computations. [ABSTRACT FROM AUTHOR]

Compressive sensing (CS)-based image coding scheme has been enthusiastically studied, but it still has a poor rate-distortion performance compared with the traditional image coding techniques. In this paper, we propose a CS multi-layer residual coding scheme to rectify this problem to a certain extent. By dividing CS measurements into multi-layers and predicting a particular layer’s measurements with all its preceding layers’ measurements, we can transform CS measurements into multi-layer residual coefficients, which are easier to compress. By calculating the residual between the quantized ground-truth CS measurements and their corresponding quantized inference measurements and using Huffman coding to associate each residual quantization index with a binary code, we can reduce the redundancies among CS measurements efficiently. Besides, the prediction and quantization process is designed to be layer-independent, which can save much of the encoding time. The proposed approach introduces a novel framework for using CS in the compression domain. The experimental results show that the proposed scheme can significantly outperform JPEG2000 and approach or reach the performance of HEVC-Intra on some test images. [ABSTRACT FROM AUTHOR]

Facial landmark detection plays an important role in face analysis tasks. Moreover, it is used as a prerequisite in many facial related applications, the simplicity, as well as effectiveness, is essential in the facial landmark detection. In this paper, we propose an effective facial landmark detection network and an associated learning framework with the geometric prior-generative adversarial network. The geometric prior-generative adversarial network consists of one generator and two discriminators. The generator consists of an encoder and two decoders. The encoder predicts facial landmark points. The decoders generate a facial inner and contour geometric map from predicted landmark points. Generating face geometric maps from predicted landmark points helps the predicted landmark points to represent the face geometric information, including shape and configuration. The discriminators determine that the given geometric maps are generated from actual landmark points or estimated landmark points. Our proposed network is end-to-end trainable, and only the encoder part is used simply as the facial landmark detector in the testing stage. To verify the effectiveness of the proposed method, we have conducted comprehensive experiments with benchmark data sets. The results have shown that the proposed method achieves comparable performances over recently proposed facial landmark detection methods with a simple and effective facial landmark detection network. [ABSTRACT FROM AUTHOR]

Radial distortion, which severely hinders object detection and semantic recognition, frequently exists in images captured using a wide-angle lens. Correction of this distortion of images is crucial in many computer vision applications. In this paper, we present distortion rectification generative adversarial network (DR-GAN), a conditional generative adversarial network (GAN) for automatic radial DR. To the best of our knowledge, this is the first end-to-end trainable adversarial framework for radial distortion rectification. The DR-GAN trained using the proposed low-to-high perceptual loss learns the mapping relation between different structural images rather than estimating multifarious distortion parameters, while also realizing label-free training and one-stage rectification. As a benefit of one-stage rectification, the proposed method is extremely fast with the completion of rectification in real time. This is approximately 22 times faster than the state-of-the-art methods. The experimental results show that the DR-GAN achieves an excellent performance in both quantitative measure (PSNR and SSIM) and visual qualitative appearance. [ABSTRACT FROM AUTHOR]

IP traffic has increased significantly in recent years, and it is expected that this progress will continue. Recent studies report that the viewing of online video content accounts for a share of 1% of the global greenhouse gas emissions. To reduce the data traffic of video streaming, the new standard Versatile Video Coding (VVC) has been finalized in 2020. In this paper, the energy efficiency of two different VVC decoders is analyzed in detail. Furthermore, we propose a design space exploration that uses an algorithm based on a greedy strategy to derive coding tool profiles that optimize the energy demand of the decoder. We show that the algorithm derives optimal coding tool profiles for a subset of coding tools. Additionally, we propose profiles that reduce the energy demand of VVC decoders and provide energy savings of more than 50% for sequences with 4K resolution. Thereby, we will also show that the proposed profiles can have a lower decoding energy demand than comparable HEVC-encoded bit streams while also having a significantly lower bit rate. [ABSTRACT FROM AUTHOR]

Image captioning aims at understanding various semantic concepts (e.g., objects and relationships) from an image and integrating them in a sentence-level description. Hence, it is necessary to learn the interaction among these concepts. If we define the context of the interaction to be involved in the subject-predicate-object triplet, most current methods only focus on the single triplet for the first-order interaction to generate sentences. Intuitively, we humans are able to perceive the high-order interaction among concepts from two or more triplets to describe an image. For example, when we see the triplets man-cutting-sandwich and man-with-knife, it is natural to integrate and predict the sentence man cutting sandwich with knife. This depends on the high-order interaction between cutting and knife in different triplets. Therefore, exploiting high-order interaction is expected to benefit image captioning and focus on reasoning. In this paper, we introduce the novel high-order interaction learning method over detected objects and relationships for image captioning under the umbrella of the encoder-decoder framework. We first extract a set of object and relationship features in an image. During the encoding stage, the interactive refining network is proposed to learn high-order representations by modeling intra- and inter-object feature interaction in the self-attention fashion. During the decoding stage, the interactive fusion network is proposed to integrate object and relationship information by strengthening their high-order interaction based on language context for sentence generation. In this way, we learn the object-relationship dependencies in different stages, which can provide abundant cues for both visual understanding and caption generation. Extensive experiments show that the proposed method can achieve competitive performances against the state-of-the-art methods on MSCOCO dataset. Additional ablation studies further validate its effectiveness. [ABSTRACT FROM AUTHOR]

Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy model cannot be achieved due to serial decoding. Second, full-resolution inference often causes the out-of-memory (OOM) problem with limited GPU resources, especially for high-resolution images. Block partition is a good choice to handle the above issues, but it brings about new challenges in reducing the redundancy between blocks and eliminating block effects. To tackle the above challenges, this paper provides a learned block-based hybrid image compression (LBHIC) framework. Specifically, we introduce explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks. Superior to context modeling by linear weighting of neighbor pixels in traditional codecs, we propose a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction. Moreover, to alleviate blocking artifacts, we further propose a boundary-aware postprocessing module (BPM) with the edge importance taken into account. Extensive experiments demonstrate that the proposed LBHIC codec outperforms the VVC, with a bit-rate conservation of 4.1%, and reduces the decoding time by approximately 86.7% compared with that of state-of-the-art learned image compression methods. [ABSTRACT FROM AUTHOR]

The scalable extension of High Efficiency Video Coding, SHVC can code Ultra High-Definition (UHD) video, including 360-degree video for various devices to serve a single bitstream with different display resolutions and qualities. To improve the SHVC compression efficiency, this paper proposes a novel intra and inter-frame coding scheme by first separating the common/visually important information and then applying cuboid-based variable size block partitioning and coding process for the common/visually important information in the base layer. In cuboid-based partitioning a video frame is partitioned into arbitrary shaped rectangular regions, known as cuboids, based on the distribution of relatively homogeneous pixel values. As the cuboid adopts a variable block partitioning based on the homogeneity of the data value, the partitioned blocks have better alignment with the object boundary. Moreover, in the cuboid coding process, only the partitioning tree information and a single value for each block need to be coded which takes lower number of bits and computational time compared to the traditional SHVC base layer. To verify the performance of the proposed method we embedded the proposed scheme as a base layer into the standard SHVC reference software and used several popular UHD/360-degree videos. The experimental results indicate that the proposed scalable coding strategy achieves an average of 14.04% BD-Rate reduction and 0.61 dB BD-PSNR gain for UHD/360-video compared to the operation points provided by an SHVC conforming encoder. [ABSTRACT FROM AUTHOR]

Infrared image retains typical thermal targets while visible image preserves rich texture details, image fusion aims to reconstruct a synthesized image containing prominent targets and abundant texture details. Most of deep learning-based methods mainly focus on convolution operation to extract the local features, but do not fully consider their multi-scale characteristics and global dependencies, which may cause loss of target regions and texture details in the fused image. Towards this goal, we present a unified multi-scale densely connected fusion network in this paper, named as UNFusion. We carefully design a multi-scale encoder-decoder architecture that can efficiently extract and reconstruct multi-scale deep features. Dense skip connections are employed in both encoder and decoder sub-networks to reuse all the intermediate features of different layers and scales for fusion tasks. In the fusion layer, $L_{p} $ normalized attention models, which include three kinds of different norms, are proposed to highlight and combine these deep features from spatial and channel dimensions, and the combined spatial and channel attention maps are used to reconstruct a final fused image. We conduct extensive experiments on the public TNO and Roadscene datasets, and the results demonstrate that our UNFusion can simultaneously preserve high brightness of typical thermal targets and abundant texture details to obtain superior scene representation and better visual perception. Besides, our UNFusion achieves better fusion performance and transcends other state-of-the-art methods in terms of qualitative and quantitative comparisons. Our code is available at https://github.com/Zhishe-Wang/UNFusion. [ABSTRACT FROM AUTHOR]

In recent years, learning-based single image dehazing networks have been comprehensively developed. However, performance improvement is limited due to domain shift between trained synthetic hazy images and untrained real-world hazy images. To alleviate this issue, this paper proposes a real-world dehazing targeted training scheme which nearly realizes paired real-world data training. As a result, a Twofold Multi-scale Generative Adversarial Network (TMS-GAN) consisting of a Haze-generation GAN (HgGAN) and a Haze-removal GAN (HrGAN) is designed. HgGAN attributes real haze properties to synthetic images and HrGAN removes haze from both synthetic and generated fake realistic data under supervision. Thus, the proposed method can better adapt to real-world image dehazing using this cooperative training scheme. Meanwhile, several structural advances of TMS-GAN also improve dehazing performance. Specifically, a haze residual map based on atmospheric scattering model is deduced in HgGAN for fake realistic data generation. The dual-branch generator in HrGAN draws attention to detail restoration by one branch along with another color-branch. A plug-and-play Multi-attention Progressive Fusion Module (MAPFM) is proposed and inserted in both HgGAN and HrGAN. MAPFM incorporates multi-attention mechanism to guide multi-scale feature fusion in a progressive manner, in which Adjacency-attention Block (AAB) can capture contributing features of each level and Self-attention Block (SAB) can establish non-local dependency of feature fusion. Experiments on mainstream benchmarks show that the proposed framework is superior especially on real-world hazy images among single image dehazing methods. [ABSTRACT FROM AUTHOR]

Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The NNR standard contains compression-efficient quantization and deep context-adaptive binary arithmetic coding (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies. This paper provides an overview of the technical features and characteristics of NNR. [ABSTRACT FROM AUTHOR]

This paper presents a new approach for a scalable extension of High Efficiency Video Coding (HEVC) intra pictures. The proposed scalable intra codec targets very low complexity together with coding efficiency, and thus employs only one prediction mode, known as inter layer intra prediction. The main novelty of the codec is a new fast rate-distortion optimization approach, which is founded on the rate-distortion theory. It exploits precomputed offline information for the reduction of the computational complexity, and a new allocation process for the balancing of the coded information. The precomputed information is a set of optimal quantifiers and associated rate-distortion curves for predetermined statistical models that are used for efficiently coding the Discrete Cosine Transform channels. This low-complexity intra coding tool has been proposed to the scalable HEVC call for proposals. In the scalable standard testing conditions, the proposed intra codec shows compression performance with a bit-rate increase of around 10% only compared with the HEVC single-layer encoder. [ABSTRACT FROM AUTHOR]

Recent research on joint source channel coding (JSCC) for wireless communications has achieved great success owing to the employment of deep learning (DL). However, the existing work on DL based JSCC usually trains the designed network to operate under a specific signal-to-noise ratio (SNR) regime, without taking into account that the SNR level during the deployment stage may differ from that during the training stage. A number of networks are required to cover the scenario with a broad range of SNRs, which is computational inefficiency (in the training stage) and requires large storage. To overcome these drawbacks our paper proposes a novel method called Attention DL based JSCC (ADJSCC) that can successfully operate with different SNR levels during transmission. This design is inspired by the resource assignment strategy in traditional JSCC, which dynamically adjusts the compression ratio in source coding and the channel coding rate according to the channel SNR. This is achieved by resorting to attention mechanisms because these are able to allocate computing resources to more critical tasks. Instead of applying the resource allocation strategy in traditional JSCC, the ADJSCC uses the channel-wise soft attention to scaling features according to SNR conditions. We compare the ADJSCC method with the state-of-the-art DL based JSCC method through extensive experiments to demonstrate its adaptability, robustness and versatility. Compared with the existing methods, the proposed method takes less storage and is more robust in the presence of channel mismatch. [ABSTRACT FROM AUTHOR]

Infrared and visible image fusion (IVIF) expects to obtain images that retain thermal radiation information from infrared images and texture details from visible images. In this paper, a model-based convolutional neural network (CNN) model, referred to as Algorithm Unrolling Image Fusion (AUIF), is proposed to overcome the shortcomings of traditional CNN-based IVIF models. The proposed AUIF model starts with the iterative formulas of two traditional optimization models, which are established to accomplish two-scale decomposition, i.e., separating low-frequency base information and high-frequency detail information from source images. Then the algorithm unrolling is implemented where each iteration is mapped to a CNN layer and each optimization model is transformed into a trainable neural network. Compared with the general network architectures, the proposed framework combines the model-based prior information and is designed more reasonably. After the unrolling operation, our model contains two decomposers (encoders) and an additional reconstructor (decoder). In the training phase, this network is trained to reconstruct the input image. While in the test phase, the base (or detail) decomposed feature maps of infrared/visible images are merged respectively by an extra fusion layer, and then the decoder outputs the fusion image. Qualitative and quantitative comparisons demonstrate the superiority of our model, which can robustly generate fusion images containing highlight targets and legible details, exceeding the state-of-the-art methods. Furthermore, our network has fewer weights and faster speed. [ABSTRACT FROM AUTHOR]

Contexts play an important role in salient object detection (SOD). High-level contexts describe the relations between different parts/objects and thus are helpful for discovering the specific locations of salient objects while low-level contexts could provide the fine detail information for delineating the boundary of the salient objects. However, the way of perceiving/leveraging rich contexts has not been fully investigated by existing SOD works. The common context extraction strategies (e.g., leveraging convolutions with large kernels or atrous convolutions with large dilation rates) do not consider the effectiveness and efficiency simultaneously and may cause sub-optimal solutions. In this paper, we devote to exploring an effective and efficient way to learn rich contexts for accurate SOD. Specifically, we first build a dense context exploration (DCE) module to capture dense multi-scale contexts and further leverage the learned contexts to enhance the features discriminability. Then, we embed multiple DCE modules in an encoder-decoder architecture to harvest dense contexts of different levels. Furthermore, we propose an attentive skip-connection to transmit useful features from the encoder part to the decoder part for better dense context exploration. Finally, extensive experiments demonstrate that the proposed method achieves more superior detection results on the six benchmark datasets than 18 state-of-the-art SOD methods. [ABSTRACT FROM AUTHOR]

In recent years, computer-generated texts, graphics, and animations have drawn more attention than ever. These types of media, also known as screen content, have become increasingly popular due to their widespread applications. To address the need for efficient coding of such content, several coding tools have been developed and have made great advances in terms of coding efficiency. The inclusion of screen content coding features in some recently developed video coding standards (namely, HEVC SCC, VVC, AVS3, AV1 and EVC) demonstrates the importance of supporting such features. This paper provides an overview and comparative study of screen content coding technologies, as well as discussions on the performance and complexity of the tools developed in these standards. [ABSTRACT FROM AUTHOR]

Inter-prediction based on block-based motion estimation (ME) is used in most video codecs. The closer the prediction to the target block, the lower the residual, and thus more efficient compression can be achieved. In this paper, a new technique called enhanced inter-prediction (EIP) is proposed to improve the prediction candidates using an additional transformation acting while performing ME. A parametric transformation acts within the coding loop of each block to modify the prediction for each motion vector candidate. The EIP is validated in the particular case of a single-parameter shifting transformation. This paper presents an efficient algorithm to compute the best shift for each prediction candidate and a model to select the optimal prediction based on minimum cost integrating the approach with existing rate-distortion optimization techniques in the H.264/AVC video codec. Results show significant improvements with an average of 6% bit-rate reduction compared to the original H.264/AVC. [ABSTRACT FROM PUBLISHER]

This paper presents a performance evaluation study of coding efficiency versus computational complexity for the forthcoming High Efficiency Video Coding (HEVC) standard. A thorough experimental investigation was carried out to identify the tools that most affect the encoding efficiency and computational complexity of the HEVC encoder. A set of 16 different encoding configurations was created to investigate the impact of each tool, varying the encoding parameter set and comparing the results with a baseline encoder. This paper shows that, even though the computational complexity increases monotonically from the baseline to the most complex configuration, the encoding efficiency saturates at some point. Moreover, the results of this paper provide relevant information for implementation of complexity-constrained encoders by taking into account the tradeoff between complexity and coding efficiency. It is shown that low-complexity encoding configurations, defined by careful selection of coding tools, achieve coding efficiency comparable to that of high-complexity configurations. [ABSTRACT FROM PUBLISHER]