Search

Video Shadow Detection (VSD) aims to detect the shadow masks with frame sequence. Existing works suffer from inefficient temporal learning. Moreover, few works address the VSD problem by considering the characteristic (i.e., boundary) of shadow. Motivated by this, we propose a Timeline and Boundary Guided Diffusion (TBGDiff) network for VSD where we take account of the past-future temporal guidance and boundary information jointly. In detail, we design a Dual Scale Aggregation (DSA) module for better temporal understanding by rethinking the affinity of the long-term and short-term frames for the clipped video. Next, we introduce Shadow Boundary Aware Attention (SBAA) to utilize the edge contexts for capturing the characteristics of shadows. Moreover, we are the first to introduce the Diffusion model for VSD in which we explore a Space-Time Encoded Embedding (STEE) to inject the temporal guidance for Diffusion to conduct shadow detection. Benefiting from these designs, our model can not only capture the temporal information but also the shadow property. Extensive experiments show that the performance of our approach overtakes the state-of-the-art methods, verifying the effectiveness of our components. We release the codes, weights, and results at \url{https://github.com/haipengzhou856/TBGDiff}., Comment: ACM MM2024

Recent advances in language models have demonstrated their capability to solve mathematical reasoning problems, achieving near-perfect accuracy on grade-school level math benchmarks like GSM8K. In this paper, we formally study how language models solve these problems. We design a series of controlled experiments to address several fundamental questions: (1) Can language models truly develop reasoning skills, or do they simply memorize templates? (2) What is the model's hidden (mental) reasoning process? (3) Do models solve math questions using skills similar to or different from humans? (4) Do models trained on GSM8K-like datasets develop reasoning skills beyond those necessary for solving GSM8K problems? (5) What mental process causes models to make reasoning mistakes? (6) How large or deep must a model be to effectively solve GSM8K-level math questions? Our study uncovers many hidden mechanisms by which language models solve mathematical questions, providing insights that extend beyond current understandings of LLMs., Comment: video appeared in ICML 2024 tutorial

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system modular design facilitates the fast integration of new tasks and models, enhancing its flexibility and scalability for various applications.

Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation., Comment: 21 pages, 9 figures

Building an embodied agent system with a large language model (LLM) as its core is a promising direction. Due to the significant costs and uncontrollable factors associated with deploying and training such agents in the real world, we have decided to begin our exploration within the Minecraft environment. Our STEVE Series agents can complete basic tasks in a virtual environment and more challenging tasks such as navigation and even creative tasks, with an efficiency far exceeding previous state-of-the-art methods by a factor of $2.5\times$ to $7.3\times$. We begin our exploration with a vanilla large language model, augmenting it with a vision encoder and an action codebase trained on our collected high-quality dataset STEVE-21K. Subsequently, we enhanced it with a Critic and memory to transform it into a complex system. Finally, we constructed a hierarchical multi-agent system. Our recent work explored how to prune the agent system through knowledge distillation. In the future, we will explore more potential applications of STEVE agents in the real world., Comment: CVPR 2024 Embodied AI Workshop

The objective of single image dehazing is to restore hazy images and produce clear, high-quality visuals. Traditional convolutional models struggle with long-range dependencies due to their limited receptive field size. While Transformers excel at capturing such dependencies, their quadratic computational complexity in relation to feature map resolution makes them less suitable for pixel-to-pixel dense prediction tasks. Moreover, fixed kernels or tokens in most models do not adapt well to varying blur sizes, resulting in suboptimal dehazing performance. In this study, we introduce a novel dehazing network based on Parallel Stripe Cross Attention (PCSA) with a multi-scale strategy. PCSA efficiently integrates long-range dependencies by simultaneously capturing horizontal and vertical relationships, allowing each pixel to capture contextual cues from an expanded spatial domain. To handle different sizes and shapes of blurs flexibly, We employs a channel-wise design with varying convolutional kernel sizes and strip lengths in each PCSA to capture context information at different scales.Additionally, we incorporate a softmax-based adaptive weighting mechanism within PCSA to prioritize and leverage more critical features., Comment: 10 pages , 4 figures, CTISC'24

Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose MovieChat to overcome these challenges. We lift pre-trained multi-modal large language models for understanding long videos without incorporating additional trainable temporal modules, employing a zero-shot approach. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method. The code along with the dataset can be accessed via the following https://github.com/rese1f/MovieChat.

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field., Comment: NTIRE 2024 Challenge Report

Deep Learning (DL) Models for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), while delivering improved performance, have been shown to be quite vulnerable to adversarial attacks. Existing works improve robustness by training models on adversarial samples. However, by focusing mostly on attacks that manipulate images randomly, they neglect the real-world feasibility of such attacks. In this paper, we propose FACTUAL, a novel Contrastive Learning framework for Adversarial Training and robust SAR classification. FACTUAL consists of two components: (1) Differing from existing works, a novel perturbation scheme that incorporates realistic physical adversarial attacks (such as OTSA) to build a supervised adversarial pre-training network. This network utilizes class labels for clustering clean and perturbed images together into a more informative feature space. (2) A linear classifier cascaded after the encoder to use the computed representations to predict the target labels. By pre-training and fine-tuning our model on both clean and adversarial samples, we show that our model achieves high prediction accuracy on both cases. Our model achieves 99.7% accuracy on clean samples, and 89.6% on perturbed samples, both outperforming previous state-of-the-art methods., Comment: 2024 IEEE Radar Conference

Adversarial attacks have demonstrated the vulnerability of Machine Learning (ML) image classifiers in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems. An adversarial attack can deceive the classifier into making incorrect predictions by perturbing the input SAR images, for example, with a few scatterers attached to the on-ground objects. Therefore, it is critical to develop robust SAR ATR systems that can detect potential adversarial attacks by leveraging the inherent uncertainty in ML classifiers, thereby effectively alerting human decision-makers. In this paper, we propose a novel uncertainty-aware SAR ATR for detecting adversarial attacks. Specifically, we leverage the capability of Bayesian Neural Networks (BNNs) in performing image classification with quantified epistemic uncertainty to measure the confidence for each input SAR image. By evaluating the uncertainty, our method alerts when the input SAR image is likely to be adversarially generated. Simultaneously, we also generate visual explanations that reveal the specific regions in the SAR image where the adversarial scatterers are likely to to be present, thus aiding human decision-making with hints of evidence of adversarial attacks. Experiments on the MSTAR dataset demonstrate that our approach can identify over 80% adversarial SAR images with fewer than 20% false alarms, and our visual explanations can identify up to over 90% of scatterers in an adversarial SAR image.

Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically accurate, faithful to text, and of good low-level quality. We present VersaT2I, a versatile training framework that can boost the performance with multiple rewards of any T2I model. We decompose the quality of the image into several aspects such as aesthetics, text-image alignment, geometry, low-level quality, etc. Then, for every quality aspect, we select high-quality images in this aspect generated by the model as the training set to finetune the T2I model using the Low-Rank Adaptation (LoRA). Furthermore, we introduce a gating function to combine multiple quality aspects, which can avoid conflicts between different quality aspects. Our method is easy to extend and does not require any manual annotation, reinforcement learning, or model architecture changes. Extensive experiments demonstrate that VersaT2I outperforms the baseline methods across various quality criteria.

Two-dimensional (2D) heterostructuring is a versatile methodology for designing nanoarchitecture catalytic systems that allow for reconstruction and modulation of interfaces and electronic structures. However, catalysts with such structures are extremely scarce due to limited synthetic strategies. Here, we report a highly ordered 2D Ru/Si nano-heterostructures (RSHS) by acid etching of the LaRuSi electride. RSHS shows a superior electrocatalytic activity for hydrogen evolution with an overpotential of 14 mV at 10 mA/cm2 in alkaline media. Both experimental analysis and first-principles calculations demonstrate that the electronic states of Ru can be tuned by strong interactions of the interfacial Ru-Si, leading to an optimized hydrogen adsorption energy. Moreover, due to the synergistic effect of Ru and Si, the energy barrier of water dissociation is significantly reduced. The unique nanostripe structure with abundant interfaces in RSHS will provide a paradigm for construction of efficient catalysts with tunable electronic states and dual active sites., Comment: 20 pages, 5 figures

Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact with the environment and coordinate their actions with other agents to achieve common objectives. However, traditional approaches often struggle to efficiently manage inter-agent communication and task distribution, crucial for effective multi-agent navigation. Furthermore, processing and integrating multi-modal information (such as visual, textual, and auditory data) is essential for agents to comprehend their goals and navigate the environment successfully and fully. To address this issue, we design the HAS framework to auto-organize groups of LLM-based agents to complete navigation tasks. In our approach, we devise a hierarchical auto-organizing navigation system, which is characterized by 1) a hierarchical system for multi-agent organization, ensuring centralized planning and decentralized execution; 2) an auto-organizing and intra-communication mechanism, enabling dynamic group adjustment under subtasks; 3) a multi-modal information platform, facilitating multi-modal perception to perform the three navigation tasks with one system. To assess organizational behavior, we design a series of navigation tasks in the Minecraft environment, which includes searching and exploring. We aim to develop embodied organizations that push the boundaries of embodied AI, moving it towards a more human-like organizational structure., Comment: ICLR 2024 Workshop on LLM Agents

The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and widespread adoption in this task. Mamba, as a State Space Model (SSM), recently emerged as a notable manner for long-range dependencies in sequential modeling, excelling in natural language processing filed with its remarkable memory efficiency and computational speed. Inspired by its success, we introduce SegMamba, a novel 3D medical image \textbf{Seg}mentation \textbf{Mamba} model, designed to effectively capture long-range dependencies within whole volume features at every scale. Our SegMamba, in contrast to Transformer-based methods, excels in whole volume feature modeling from a state space model standpoint, maintaining superior processing speed, even with volume features at a resolution of {$64\times 64\times 64$}. Comprehensive experiments on the BraTS2023 dataset demonstrate the effectiveness and efficiency of our SegMamba. The code for SegMamba is available at: https://github.com/ge-xing/SegMamba, Comment: Code has released

Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and directly fitting end-to-end networks, leading to inconsistent illumination, or rely on unreliable handcrafted priors to constrain the network, thereby bringing the greater error to the final result. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks. To ensure the faithful restoration of details and illumination, we propose the incorporation of two essential modules: the Adaptive Illumination Enhancement Module (AIEM) and the Deformable Bi-directional Cross-Attention (DBCA) module. The AIEM leverages the inter-channel correlation of features to dynamically maintain illumination consistency between degraded features and high-quality codebook features. Meanwhile, the DBCA module effectively integrates texture and structural information through bi-directional cross-attention and deformable convolution, resulting in enhanced fine-grained detail and structural fidelity across parallel decoders. Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets. The code is available at https://github.com/AlexZou14/VQCNIR., Comment: This paper is accepted by AAAI2024

Synthetic Aperture Radar SAR Automatic Target Recognition ATR is a key technique of remote-sensing image recognition which can be supported by deep neural networks The existing works of SAR ATR mostly focus on improving the accuracy of the target recognition while ignoring the systems performance in terms of speed and storage which is critical to real-world applications of SAR ATR For decision-makers aiming to identify a proper deep learning model to deploy in a SAR ATR system it is important to understand the performance of different candidate deep learning models and determine the best model accordingly This paper comprehensively benchmarks several advanced deep learning models for SAR ATR with multiple distinct SAR imagery datasets Specifically we train and test five SAR image classifiers based on Residual Neural Networks ResNet18 ResNet34 ResNet50 Graph Neural Network GNN and Vision Transformer for Small-Sized Datasets (SS-ViT) We select three datasets MSTAR GBSAR and SynthWakeSAR that offer heterogeneity We evaluate and compare the five classifiers concerning their classification accuracy runtime performance in terms of inference throughput and analytical performance in terms of number of parameters number of layers model size and number of operations Experimental results show that the GNN classifier outperforms with respect to throughput and latency However it is also shown that no clear model winner emerges from all of our chosen metrics and a one model rules all case is doubtful in the domain of SAR ATR, Comment: 6 Pages

Adversarial attacks have highlighted the vulnerability of classifiers based on machine learning for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) tasks. An adversarial attack perturbs SAR images of on-ground targets such that the classifiers are misled into making incorrect predictions. However, many existing attacking techniques rely on arbitrary manipulation of SAR images while overlooking the feasibility of executing the attacks on real-world SAR imagery. Instead, adversarial attacks should be able to be implemented by physical actions, for example, placing additional false objects as scatterers around the on-ground target to perturb the SAR image and fool the SAR ATR. In this paper, we propose the On-Target Scatterer Attack (OTSA), a scatterer-based physical adversarial attack. To ensure the feasibility of its physical execution, we enforce a constraint on the positioning of the scatterers. Specifically, we restrict the scatterers to be placed only on the target instead of in the shadow regions or the background. To achieve this, we introduce a positioning score based on Gaussian kernels and formulate an optimization problem for our OTSA attack. Using a gradient ascent method to solve the optimization problem, the OTSA can generate a vector of parameters describing the positions, shapes, sizes and amplitudes of the scatterers to guide the physical execution of the attack that will mislead SAR image classifiers. The experimental results show that our attack obtains significantly higher success rates under the positioning constraint compared with the existing method.

Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. STEVE comprises three key components: vision perception, language instruction, and code action. Vision perception involves interpreting visual information in the environment, which is then integrated into the LLMs component with agent state and task instruction. Language instruction is responsible for iterative reasoning and decomposing complex tasks into manageable guidelines. Code action generates executable skill actions based on retrieval in skill database, enabling the agent to interact effectively within the Minecraft environment. We also collect STEVE-21K dataset, which includes 600+ vision-environment pairs, 20K knowledge question-answering pairs, and 200+ skill-code pairs. We conduct continuous block search, knowledge question and answering, and tech tree mastery to evaluate the performance. Extensive experiments show that STEVE achieves at most 1.5x faster unlocking key tech trees and 2.5x quicker in block search tasks., Comment: ECCV 2024. First three authors contribute equally to this work. Project Website https://rese1f.github.io/STEVE/

Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). To ensure detailed reconstruction and illumination correction, RLDM is empowered to acquire Retinex knowledge and extract reflectance and illumination priors. These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates the decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments show that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications. Code will be available at \url{https://github.com/ChunmingHe/Reti-Diff}., Comment: 20 pages, 11 figures, 11 tables

In this paper, we propose a novel semiquantum proxy blind signature scheme with quantum teleportation based on X states, where the original message owner, the proxy signer and the third party are quantum participants with complete quantum capabilities, while the original signer and the signature verifier are semiquantum participants with limited quantum capabilities. It turns out that our protocol not only has complete blindness, unforgeability, non-repudiation and but also can resist the attack behavior from an eavesdropper. Compared with many previous quantum proxy blind signature protocols, our protocol may need less quantum resources and be easier to implement in reality, since both the original signer and the signature verifier are semiquantum participants with limited quantum capabilities., Comment: 15 pages,1 figure,3 tables

In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of image editing tasks, especially for interior design scenes. By surveying existing object editing methodologies, we distill three essential criteria -- consistency, controllability, and harmony -- that should be met for an image editing method. In contrast to previous approaches, our framework takes the lead in satisfying all three requirements for addressing the challenge of image synthesis. Through comprehensive experiments, encompassing both quantitative assessments and qualitative comparisons with contemporary state-of-the-art methods, we present compelling evidence of our framework's superior performance across multiple dimensions. This work establishes a promising avenue for advancing image synthesis techniques and empowering precise object modifications while preserving the visual coherence of the entire composition., Comment: Accepted by IJCAI 2024

In this paper, we design the first semiquantum private comparison (SQPC) protocol which is realized via cavity quantum electrodynamics (QED) by making use of the evolution law of atom. With the help of a semi-honest third party (TP), the proposed protocol can compare the equality of private inputs from two semiquantum parties who only have limited quantum capabilities. The proposed protocol uses product states as initial quantum resource and employs none of unitary operations, quantum entanglement swapping operation or delay lines. Security proof turns out that it can defeat both the external attack and the internal attack., Comment: 21 pages, 7 figures, 2 tables

In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image. Note that the rain streaks and raindrops have diverse shapes, sizes, and locations in the captured image, and thus modeling the correlation relationship between irregular degradations caused by rain artifacts is a necessary prerequisite for image deraining. This paper aims to present an efficient and flexible mechanism to learn and model degradation relationships in a global view, thereby achieving a unified removal of intricate rain scenes. To do so, we propose a Sparse Sampling Transformer based on Uncertainty-Driven Ranking, dubbed UDR-S2Former. Compared to previous methods, our UDR-S2Former has three merits. First, it can adaptively sample relevant image degradation information to model underlying degradation relationships. Second, explicit application of the uncertainty-driven ranking strategy can facilitate the network to attend to degradation features and understand the reconstruction process. Finally, experimental results show that our UDR-S2Former clearly outperforms state-of-the-art methods for all benchmarks., Comment: Accepted by ICCV'23

In this paper, a novel hybrid protocol for semiquantum key distribution (SQKD) and semiquantum secret sharing (SQSS) was constructed by using GHZ-like states. This protocol is capable of establishing two different private keys between one quantum party and two semiquantum parties respectively, and making two semiquantum parties share another private key of the quantum party in the meanwhile. The usages of delay lines, Pauli operations, Hadamard gates and quantum entanglement swapping are not required. Moreover, the semiquantum parties are not necessary to be equipped with any quantum memory. We validate in detail that this protocol resists various attacks from Eve, including the Trojan horse attacks, the entangle-measure attack, the double controlled-not (CNOT) attacks, the measure-resend attack and the intercept-resend attack. To our best knowledge, this protocol is the only protocol which possesses the functions of both SQKD and SQSS simultaneously until now., Comment: 16 pages,1 figure, 3 tables

Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method., Comment: CVPR 2024. First three authors contribute equally to this work. Project Website https://rese1f.github.io/MovieChat/

Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose representations in the shared feature space. In this paper, we propose \mpm, a unified 2D-3D human pose representation framework via masked pose modeling. We treat 2D and 3D poses as two different modalities like vision and language and build a single-stream transformer-based architecture. We apply two pretext tasks, which are masked 2D pose modeling, and masked 3D pose modeling to pre-train our network and use full-supervision to perform further fine-tuning. A high masking ratio of $71.8~\%$ in total with a spatio-temporal mask sampling strategy leads to better relation modeling both in spatial and temporal domains. \mpm~can handle multiple tasks including 3D human pose estimation, 3D pose estimation from occluded 2D pose, and 3D pose completion in a \textbf{single} framework. We conduct extensive experiments and ablation studies on several widely used human pose datasets and achieve state-of-the-art performance on MPI-INF-3DHP., Comment: Accepted by PRCV2024

In this paper, we adopt \c{hi}-type states to design a novel circular semiquantum private comparison (SQPC) protocol which can determine the equality of private inputs from two semiquantum users within one round implementation under the help of a semi-honest third party (TP) who possesses complete quantum capabilities. Here, it is assumed that the semi-honest TP has the abilities to launch all possible attacks to steal useful information about two semiquantum users' private inputs but cannot conspire with anyone else. The travelling particles go from TP to Alice, Alice to Bob and back from Bob to TP. The security analysis turns out the proposed SQPC protocol can resist both the outside attacks and the inside attacks. The proposed SQPC protocol has no demand for unitary operations. Compared with some existing SQPC protocols of equality with quantum entangled states, the proposed SQPC protocol has some advantages more or less:(1)it requires no pre-shared key among different participants; (2)it doesn't need quantum entanglement swapping; and(3)it employs no delay lines., Comment: 32 pages,3 figures,3 tables

Nighttime image dehazing is a challenging task due to the presence of multiple types of adverse degrading effects including glow, haze, blurry, noise, color distortion, and so on. However, most previous studies mainly focus on daytime image dehazing or partial degradations presented in nighttime hazy scenes, which may lead to unsatisfactory restoration results. In this paper, we propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. During the pre-training stage, we introduce two powerful priors into the transformer decoder to generate the non-learnable prior queries, which guide the model to extract specific degradations. For the fine-tuning, we combine the generated pseudo ground truths with input real-world nighttime hazy images as paired images and feed into the synthetic domain to fine-tune the pre-trained model. This semi-supervised fine-tuning paradigm helps improve the generalization to real domain. In addition, we also propose a large-scale synthetic dataset called UNREAL-NH, to simulate the real-world nighttime haze scenarios comprehensively. Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively., Comment: 10 pages, 11 figures

A lightweight underwater image enhancement network is of great significance for resource-constrained platforms, but balancing model size, computational efficiency, and enhancement performance has proven difficult for previous approaches. In this work, we propose the Five A$^{+}$ Network (FA$^{+}$Net), a highly efficient and lightweight real-time underwater image enhancement network with only $\sim$ 9k parameters and $\sim$ 0.01s processing time. The FA$^{+}$Net employs a two-stage enhancement structure. The strong prior stage aims to decompose challenging underwater degradations into sub-problems, while the fine-grained stage incorporates multi-branch color enhancement module and pixel attention module to amplify the network's perception of details. To the best of our knowledge, FA$^{+}$Net is the only network with the capability of real-time enhancement of 1080P images. Thorough extensive experiments and comprehensive visual comparison, we show that FA$^{+}$Net outperforms previous approaches by obtaining state-of-the-art performance on multiple datasets while significantly reducing both parameter count and computational complexity. The code is open source at https://github.com/Owen718/FiveAPlus-Network.

Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges. Recent learning-based depth estimation methods are mainly targeted at dehazing first and estimating depth subsequently from haze-free scenes. This way, the inner connections between colored haze and scene depth are lost. In this paper, we propose a real-time transformer for simultaneous single image Depth Estimation and Haze Removal (DEHRFormer). DEHRFormer consists of a single encoder and two task-specific decoders. The transformer decoders with learnable queries are designed to decode coupling features from the task-agnostic encoder and project them into clean image and depth map, respectively. In addition, we introduce a novel learning paradigm that utilizes contrastive learning and domain consistency learning to tackle weak-generalization problem for real-world dehazing, while predicting the same depth map from the same scene with varicolored haze. Experiments demonstrate that DEHRFormer achieves significant performance improvement across diverse varicolored haze scenes over previous depth estimation networks and dehazing approaches., Comment: Accepted to ICASSP'2023

Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles. To address this issue, we propose a Real-time Spatial and Frequency Domains Modulation Network (RSFDM-Net) for the efficient enhancement of colors and details in underwater images. Specifically, our proposed conditional network is designed with Adaptive Fourier Gating Mechanism (AFGM) and Multiscale Convolutional Attention Module (MCAM) to generate vectors carrying low-frequency background information and high-frequency detail features, which effectively promote the network to model global background information and local texture details. To more precisely correct the color cast and low saturation of the image, we introduce a Three-branch Feature Extraction (TFE) block in the primary net that processes images pixel by pixel to integrate the color information extended by the same channel (R, G, or B). This block consists of three small branches, each of which has its own weights. Extensive experiments demonstrate that our network significantly outperforms over state-of-the-art methods in both visual quality and quantitative metrics.

In this paper, we put forward a multi-party quantum private comparison (MQPC) protocol with two semi-honest third parties (TPs) by adopting d-dimensional Bell states, which can judge the size relationship of private integers from more than two users within one execution of protocol. Each TP is permitted to misbehave on her own but cannot collude with others. In the proposed MQPC protocol, TPs are only required to apply d-dimensional single-particle measurements rather than d-dimensional Bell state measurements. There are no quantum entanglement swapping and unitary operations required in the proposed MQPC protocol. The security analysis validates that the proposed MQPC protocol can resist both the outside attacks and the participant attacks. The proposed MQPC protocol is adaptive for the case that users want to compare the size relationship of their private integers under the control of two supervisors. Furthermore, the proposed MQPC protocol can be used in the strange user environment, because there are not any communication and pre-shared key between each pair of users., Comment: 15 pages, 1 figure, 1 table

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose critical insight is to combine the powerful global modeling ability of self-attention modules and the local modeling ability of convolutions in an overall architecture. With convolution-based Local Feature Extraction modules equipped in the encoder and the decoder, we only adopt a novel Hybrid Transformer Block in the latent layer to model the long-distance dependence in spatial dimensions and handle the uneven distribution between channels. Such a design eliminates the substantial computational complexity in previous image restoration transformers and achieves superior performance on multiple image restoration tasks. Experiments demonstrate that Dual-former achieves a 1.91dB gain over the state-of-the-art MAXIM method on the Indoor dataset for single image dehazing while consuming only 4.2% GFLOPs as MAXIM. For single image deraining, it exceeds the SOTA method by 0.1dB PSNR on the average results of five datasets with only 21.5% GFLOPs. Dual-former also substantially surpasses the latest desnowing method on various datasets, with fewer parameters.

A single-state multiparty semiquantum secret sharing (MSQSS) scheme with d-dimensional Bell states is proposed, which can accomplish the goal that only when all receivers work together can they restore the sender's secret key. This protocol is validated to be secure against both the outside attack and the participant attack. This protocol is adaptive for the d-dimensional system, only employs one kind of d-dimensional Bell states as initial quantum resource and needs neither quantum entanglement swapping nor unitary operations., Comment: 9 pages, 1 figure, 1 table

By using d-level single-particle states, the first multi-party semiquantum private comparison (MSQPC) protocol which can judge the size relationship of private inputs from more than two classical users within one execution of protocol is put forward. This protocol requires the help of one quantum third party (TP) and one classical TP, both of whom are allowed to misbehave on their own but cannot conspire with anyone else. Neither quantum entanglement swapping nor unitary operations are necessary for implementing this protocol. TPs are only required to perform d-dimensional single-particle measurements. The correctness analysis validates the accuracy of the compared results. The security analysis verifies that both the outside attacks and the participant attacks can be resisted., Comment: 19 pages, 2 figures, 2 tables

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR., Comment: Camera-ready version

Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions to build local-global context interaction across patches and surpasses existing works that employ local operators or vanilla transformers. Compared to prior desnowing methods and universal image restoration methods, SnowFormer has several benefits. Firstly, unlike the multi-head self-attention in recent image restoration Vision Transformers, SnowFormer incorporates the multi-head cross-attention mechanism to perform local-global context interaction between scale-aware snow queries and local-patch embeddings. Second, the snow queries in SnowFormer are generated by the query generator from aggregated scale-aware features, which are rich in potential clean cues, leading to superior restoration results. Third, SnowFormer outshines advanced state-of-the-art desnowing networks and the prevalent universal image restoration transformers on six synthetic and real-world datasets. The code is released in \url{https://github.com/Ephemeral182/SnowFormer}.

In this paper, a semiquantum secret sharing (SQSS) protocol based on x-type states is proposed, which can accomplish the goal that only when two classical communicants cooperate together can they extract the shared secret key of a quantum communicant. Detailed security analysis turns out that this protocol is completely robust against an eavesdropper. This protocol has some merits: (1) it only requires one kind of quantum entangled state as the initial quantum resource; (2) it doesn't employ quantum entanglement swapping or unitary operations; and (3) it needn't share private keys among different participants beforehand., Comment: 20 pages, 1 figure, 3 tables

Snow removal causes challenges due to its characteristic of complex degradations. To this end, targeted treatment of multi-scale snow degradations is critical for the network to learn effective snow removal. In order to handle the diverse scenes, we propose a multi-scale projection transformer (MSP-Former), which understands and covers a variety of snow degradation features in a multi-path manner, and integrates comprehensive scene context information for clean reconstruction via self-attention operation. For the local details of various snow degradations, the local capture module is introduced in parallel to assist in the rebuilding of a clean image. Such design achieves the SOTA performance on three desnowing benchmark datasets while costing the low parameters and computational complexity, providing a guarantee of practicality., Comment: Accepted to ICASSP'2023

In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation is varied from image to image. Recent methods adopt deep neural networks to directly recover clean scenes from snowy images. However, due to the paradox caused by the variation of complex snowy degradation, achieving reliable High-Definition image desnowing performance in real time is a considerable challenge. We develop a novel Efficient Pyramid Network with asymmetrical encoder-decoder architecture for real-time HD image desnowing. The general idea of our proposed network is to utilize the multi-scale feature flow fully and implicitly mine clean cues from features. Compared with previous state-of-the-art desnowing methods, our approach achieves a better complexity-performance trade-off and effectively handles the processing difficulties of HD and Ultra-HD images. The extensive experiments on three large-scale image desnowing datasets demonstrate that our method surpasses all state-of-the-art approaches by a large margin both quantitatively and qualitatively, boosting the PSNR metric from 31.76 dB to 34.10 dB on the CSD test dataset and from 28.29 dB to 30.87 dB on the SRRS test dataset.

Neural architecture search methods seek optimal candidates with efficient weight-sharing supernet training. However, recent studies indicate poor ranking consistency about the performance between stand-alone architectures and shared-weight networks. In this paper, we present Prior-Guided One-shot NAS (PGONAS) to strengthen the ranking correlation of supernets. Specifically, we first explore the effect of activation functions and propose a balanced sampling strategy based on the Sandwich Rule to alleviate weight coupling in the supernet. Then, FLOPs and Zen-Score are adopted to guide the training of supernet with ranking correlation loss. Our PGONAS ranks 3rd place in the supernet Track Track of CVPR2022 Second lightweight NAS challenge. Code is available in https://github.com/pprp/CVPR2022-NAS?competition-Track1-3th-solution., Comment: Official 3st Place Solution for the Second workshop Neural Architecture Search Second lightweight NAS Challenge 2022 - Track1 Supernet Track. Official leaderboard: https://aistudio.baidu.com/aistudio/competition/detail/149/0/leaderboard CVPR 2022 Workshop: https://cvpr-nas.com/competition

In this paper, a three-party secure semiquantum summation protocol, which can calculate the modulo 2 addition of the private bits from one quantum participant and two classical participants, is constructed by only using single qubits as the initial quantum resource. This protocol needs none of quantum entanglement swapping, the unitary operation or a pre-shared private key. This protocol only requires the quantum participant to perform the Z basis measurements, the X basis measurements and the Bell basis measurements. Compared with the existing only semiquantum summation protocol (Int J Theor Phys, 60 (2021) 3478), this protocol has better performance in quantum measurements for quantum participant; moreover, it may also have higher qubit efficiency., Comment: 11 pages, 1 table

In this paper, we propose a two-party semiquantum summation protocol, where two classical users can accomplish the summation of their private binary sequences with the assistance of a quantum semi-honest third party (TP). The term 'semi-honest' implies that TP cannot conspire with others but is able to implement all kinds oof attacks. This protocol employs logical qubits as traveling particles to overcome the negative influence of collective-dephasing noise and needn't make any two parties pre-share a random secret key. The security analysis turns out that this protocol can effectively prevent the outside attacks from Eve and the participant attacks from TP. Moreover, TP has no knowledge about the summation results., Comment: 9 pages, 2 tables

In this paper, a novel information leakage resistant quantum dialogue (QD) protocol with single photons in both polarization and spatial-mode degrees of freedom is proposed, which utilizes quantum encryption technology to overcome the information leakage problem. In the proposed QD protocol, during the transmission process, the single photons in both polarization and spatial-mode degrees of freedom used for encoding two communicants' private classical bits are protected by both quantum encryption technology and decoy photon technology. For avoiding the information leakage problem, the initial states of the single photons in both polarization and spatial-mode degrees of freedom used for encoding two communicants' private classical bits are shared between two communicants through quantum key encryption and decryption. The information-theoretical efficiency of the proposed QD protocol is as high as 40%., Comment: 7 pages

In this paper, a multi-party quantum private comparison (MQPC) scheme is suggested based on entanglement swapping of Bell entangled states within d-level quantum system, which can accomplish the equality comparison of secret binary sequences from n users via one execution of scheme. Detailed security analysis shows that both the outside attack and the participant attack are ineffective. The suggested scheme needn't establish a private key among n users beforehand through the quantum key distribution (QKD) method to encrypt the secret binary sequences. Compared with previous MQPC scheme based on d-level Cat states and d-level Bell entangled states, the suggested scheme has distinct advantages on quantum resource, quantum measurement of third party (TP) and qubit efficiency., Comment: 8 pages, 1 figure, 1 table

In this paper, a novel quantum dialogue (QD) protocol is proposed based on single photons in both polarization and spatial-mode degrees of freedom. In the proposed QD protocol, the initial states of single photons in both polarization and spatial-mode degrees of freedom used for encoding are privately shared between two communicants through the direct transmissions of their auxiliary counterparts from one communicant to another. As a result, the information leakage problem is avoided. Moreover, the detailed security analysis also shows that the proposed QD protocol can resist Eve's several famous active attacks, such as the Trojan horse attack, the intercept-resend attack, the measure-resend attack and the entangle-measure attack. The proposed QD protocol only needs single photons in both polarization and spatial-mode degrees of freedom as quantum resource and adopts single-photon measurements. As a result, it is feasible in practice as the preparation and the measurement of a single photon in both polarization and spatial-mode degrees of freedom can be accomplished with current experimental techniques., Comment: 9 pages, 1 figure, 4 tables

In this paper, a novel multi-party quantum private comparison (MQPC) protocol for equality comparison with n-level single-particle states is constructed, where the encoded particles are transmitted in a circular way. Here, n parties employ the qudit shifting operation to encode their private secrets and can compare the equality of their private secrets within one time execution of protocol. The proposed MQPC protocol can overcome both the outside attack and the participant attack. Specially, each party's secret can be kept unknown to other parties and the third party (TP)., Comment: 11 pages, 1 table. arXiv admin note: substantial text overlap with arXiv:2205.06406

In this paper, a novel semi-quantum key distribution (SQKD) protocol is designed based on single photons in both polarization and spatial-mode degrees of freedom, which allows to establish a raw key between one quantum communicant and one classical communicant. The proposed SQKD protocol only adopts one kind of quantum state as the initial quantum resource. The detailed security analysis shows that it can resist Eve's active attacks, such as the intercept-resend attack, the measure-resend attack, the Trojan horse attack and the entangle-measure attack. The proposed SQKD protocol only needs single photons in both polarization and spatial-mode degrees of freedom as quantum resource and employs single-photon measurements. Thus, it has excellent feasibility, since the preparation and the measurement of a single photon in both polarization and spatial-mode degrees of freedom can be easily acheived with present quantum technologies., Comment: 6 pages, 2 figures, 1 tables. arXiv admin note: text overlap with arXiv:2205.06408

In this paper, we propose a novel secure multi-party quantum summation protocol based on quantum Fourier transform, where the traveling particles are transmitted in a tree-type mode. The party who prepares the initial quantum states is assumed to be semi-honest, which means that she may misbehave on her own but will not conspire with anyone. The proposed protocol can resist both the outside attacks and the participant attacks. Especially, one party cannot obtain other parties' private integer strings; and it is secure for the colluding attack performed by at most n-2 parties, where n is the number of parties. In addition, the proposed protocol calculates the addition of modulo d and implements the calculation of addition in a secret-by-secret way rather than a bit-by-bit way., Comment: 10 pages, 2 figures, 2 tables