Search

The quality of images captured outdoors is often affected by the weather. One factor that interferes with sight is rain, which can obstruct the view of observers and computer vision applications that rely on those images. The work aims to recover rain images by removing rain streaks via Self-supervised Reinforcement Learning (RL) for image deraining (SRL-Derain). We locate rain streak pixels from the input rain image via dictionary learning and use pixel-wise RL agents to take multiple inpainting actions to remove rain progressively. To our knowledge, this work is the first attempt where self-supervised RL is applied to image deraining. Experimental results on several benchmark image-deraining datasets show that the proposed SRL-Derain performs favorably against state-of-the-art few-shot and self-supervised deraining and denoising methods.

Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of the Transformer has raised awareness in the computer-vision community. However, its self-attention mechanism requires much memory, which is unsuitable for high-resolution vision tasks like video restoration. In this paper, we propose ViStripformer (Video Stripformer), which utilizes spatio-temporal strip attention to catch long-range data correlations, consisting of intra-frame strip attention (Intra-SA) and inter-frame strip attention (Inter-SA) for extracting spatial and temporal information. It decomposes video frames into strip-shaped features in horizontal and vertical directions for Intra-SA and Inter-SA to address degradation patterns with various orientations and magnitudes. Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer. Extensive experiments show that the proposed model achieves superior results with fast inference time on video restoration tasks, including video deblurring, demoireing, and deraining.

Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data augmentation for image deblurring. Since continuous motion causes blurred artifacts during image exposure, we aspire to develop a groundbreaking blur augmentation method to generate diverse blurred images by simulating motion trajectories in a continuous space. This paper proposes Implicit Diffusion-based reBLurring AUgmentation (ID-Blau), utilizing a sharp image paired with a controllable blur condition map to produce a corresponding blurred image. We parameterize the blur patterns of a blurred image with their orientations and magnitudes as a pixel-wise blur condition map to simulate motion trajectories and implicitly represent them in a continuous space. By sampling diverse blur conditions, ID-Blau can generate various blurred images unseen in the training set. Experimental results demonstrate that ID-Blau can produce realistic blurred images for training and thus significantly improve performance for state-of-the-art deblurring models. The source code is available at https://github.com/plusgood-steven/ID-Blau., Comment: CVPR 2024

Multimodal manipulations (also known as audio-visual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets.

Deepfake videos, generated through AI faceswapping techniques, have garnered considerable attention due to their potential for powerful impersonation attacks. While existing research primarily focuses on binary classification to discern between real and fake videos, however determining the specific generation model for a fake video is crucial for forensic investigation. Addressing this gap, this paper investigates the model attribution problem of Deepfake videos from a recently proposed dataset, Deepfakes from Different Models (DFDM), derived from various Autoencoder models. The dataset comprises 6,450 Deepfake videos generated by five distinct models with variations in encoder, decoder, intermediate layer, input resolution, and compression ratio. This study formulates Deepfakes model attribution as a multiclass classification task, proposing a segment of VGG19 as a feature extraction backbone, known for its effectiveness in imagerelated tasks, while integrated a Capsule Network with a Spatio-Temporal attention mechanism. The Capsule module captures intricate hierarchies among features for robust identification of deepfake attributes. Additionally, the video-level fusion technique leverages temporal attention mechanisms to handle concatenated feature vectors, capitalizing on inherent temporal dependencies in deepfake videos. By aggregating insights across frames, our model gains a comprehensive understanding of video content, resulting in more precise predictions. Experimental results on the deepfake benchmark dataset (DFDM) demonstrate the efficacy of our proposed method, achieving up to a 4% improvement in accurately categorizing deepfake videos compared to baseline models while demanding fewer computational resources., Comment: Rejected from jounal and will have to conduct several more experiments

Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts. However, these approaches might have sub-optimal deblurring results due to the domain gap between the training and test sets. This paper proposes a reblur-deblur meta-transferring scheme to realize test-time adaptation without using ground truth for dynamic scene deblurring. Since the ground truth is usually unavailable at inference time in a real-world scenario, we leverage the blurred input video to find and use relatively sharp patches as the pseudo ground truth. Furthermore, we propose a reblurring model to extract the homogenous blur from the blurred input and transfer it to the pseudo-sharps to obtain the corresponding pseudo-blurred patches for meta-learning and test-time adaptation with only a few gradient updates. Extensive experimental results show that our reblur-deblur meta-learning scheme can improve state-of-the-art deblurring models on the DVD, REDS, and RealBlur benchmark datasets., Comment: Accepted at BMVC 2022

Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality. Such blur causes short- and long-range region-specific smoothing artifacts that are often directional and non-uniform, which is difficult to be removed. Inspired by the current success of transformers on computer vision and image processing tasks, we develop, Stripformer, a transformer-based architecture that constructs intra- and inter-strip tokens to reweight image features in the horizontal and vertical directions to catch blurred patterns with different orientations. It stacks interlaced intra-strip and inter-strip attention layers to reveal blur magnitudes. In addition to detecting region-specific blurred patterns of various orientations and magnitudes, Stripformer is also a token-efficient and parameter-efficient transformer model, demanding much less memory usage and computation cost than the vanilla transformer but works better without relying on tremendous training data. Experimental results show that Stripformer performs favorably against state-of-the-art models in dynamic scene deblurring., Comment: ECCV 2022 Oral Presentation

Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multiscale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically lead to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deblurring via a single forward pass. Our BANet utilizes region-based self-attention with multi-kernel strip pooling to disentangle blur patterns of different magnitudes and orientations and cascaded parallel dilated convolution to aggregate multi-scale content features. Extensive experimental results on the GoPro and RealBlur benchmarks demonstrate that the proposed BANet performs favorably against the state-of-the-arts in blurred image restoration and can provide deblurred results in real-time., Comment: TIP 2022, Code: https://github.com/pp00704831/BANet

Images degraded by light scattering and absorption, such as hazy, sandstorm, and underwater images, often suffer color distortion and low contrast because of light traveling through turbid media. In order to enhance and restore such images, we first estimate ambient light using the depth-dependent color change. Then, via calculating the difference between the observed intensity and the ambient light, which we call the scene ambient light differential, scene transmission can be estimated. Additionally, adaptive color correction is incorporated into the image formation model (IFM) for removing color casts while restoring contrast. Experimental results on various degraded images demonstrate the new method outperforms other IFM-based methods subjectively and objectively. Our approach can be interpreted as a generalization of the common dark channel prior (DCP) approach to image restoration, and our method reduces to several DCP variants for different special cases of ambient lighting and turbid medium conditions.

Images degraded by light scattering and absorption, such as hazy, sandstorm, and underwater images, often suffer color distortion and low contrast because of light traveling through turbid media. In order to enhance and restore such images, we first estimate ambient light using the depth-dependent color change. Then, via calculating the difference between the observed intensity and the ambient light, which we call the scene ambient light differential, scene transmission can be estimated. Additionally, adaptive color correction is incorporated into the image formation model (IFM) for removing color casts while restoring contrast. Experimental results on various degraded images demonstrate the new method outperforms other IFM-based methods subjectively and objectively. Our approach can be interpreted as a generalization of the common dark channel prior (DCP) approach to image restoration, and our method reduces to several DCP variants for different special cases of ambient lighting and turbid medium conditions.

Underwater images often suffer from color distortion and low contrast, because light is scattered and absorbed when traveling through water. Such images with different color tones can be shot in various lighting conditions, making restoration and enhancement difficult. We propose a depth estimation method for underwater scenes based on image blurriness and light absorption, which can be used in the image formation model (IFM) to restore and enhance underwater images. Previous IFM-based image restoration methods estimate scene depth based on the dark channel prior or the maximum intensity prior. These are frequently invalidated by the lighting conditions in underwater images, leading to poor restoration results. The proposed method estimates underwater scene depth more accurately. Experimental results on restoring real and synthesized underwater images demonstrate that the proposed method outperforms other IFM-based underwater image restoration methods.

Images degraded by light scattering and absorption such as hazy, sandstorm, and underwater images often suffer from color distortion and low contrast because of light traveling through turbid media. This can prevent systems that operate outdoors in different lighting conditions from functioning properly, for example, video surveillance systems, autopilot systems and intelligent transportation systems, which include automatic license plate recognition, automatic traffic counting, etc. Therefore, it is desirable to develop an effective method to restore color and enhance contrast for these images. This thesis presents novel work to advance research on image restoration and enhancement for such images.To enhance or restore such a degraded image, the image formation model is often used to describe it as a ``clear" image blended with an ambient light based on the scene transmission computed using the scene depth from the camera. The transmission describes the portion of the scene radiance which is not scattered or absorbed and which reaches the camera. By reversing the image formation process, one can attain the scene radiance from a degraded image, which is a ``clear" image. However, it involves solving an ill-posed and under-constrained problem because we need to estimate both the ambient light and scene transmission from a single degraded image.To attack this problem, we proposed to use image blurriness to estimate ambient light and scene depth for underwater images. Furthermore, we extended it by combining light absorption and blurriness to estimate scene depth for underwater scenes in different lighting conditions and color tones. For any images degraded by light scattering and absorption, not limited to underwater ones, we proposed a generalization of the common dark channel prior approach for ambient light and transmission estimation. Additionally, adaptive color correction is incorporated into the image formation model for removing color casts while restoring con

Images degraded by light scattering and absorption such as hazy, sandstorm, and underwater images often suffer from color distortion and low contrast because of light traveling through turbid media. This can prevent systems that operate outdoors in different lighting conditions from functioning properly, for example, video surveillance systems, autopilot systems and intelligent transportation systems, which include automatic license plate recognition, automatic traffic counting, etc. Therefore, it is desirable to develop an effective method to restore color and enhance contrast for these images. This thesis presents novel work to advance research on image restoration and enhancement for such images.To enhance or restore such a degraded image, the image formation model is often used to describe it as a ``clear" image blended with an ambient light based on the scene transmission computed using the scene depth from the camera. The transmission describes the portion of the scene radiance which is not scattered or absorbed and which reaches the camera. By reversing the image formation process, one can attain the scene radiance from a degraded image, which is a ``clear" image. However, it involves solving an ill-posed and under-constrained problem because we need to estimate both the ambient light and scene transmission from a single degraded image.To attack this problem, we proposed to use image blurriness to estimate ambient light and scene depth for underwater images. Furthermore, we extended it by combining light absorption and blurriness to estimate scene depth for underwater scenes in different lighting conditions and color tones. For any images degraded by light scattering and absorption, not limited to underwater ones, we proposed a generalization of the common dark channel prior approach for ambient light and transmission estimation. Additionally, adaptive color correction is incorporated into the image formation model for removing color casts while restoring con

Underwater images often suffer from color distortion and low contrast, because light is scattered and absorbed when traveling through water. Such images with different color tones can be shot in various lighting conditions, making restoration and enhancement difficult. We propose a depth estimation method for underwater scenes based on image blurriness and light absorption, which can be used in the image formation model (IFM) to restore and enhance underwater images. Previous IFM-based image restoration methods estimate scene depth based on the dark channel prior or the maximum intensity prior. These are frequently invalidated by the lighting conditions in underwater images, leading to poor restoration results. The proposed method estimates underwater scene depth more accurately. Experimental results on restoring real and synthesized underwater images demonstrate that the proposed method outperforms other IFM-based underwater image restoration methods.