Underwater scenes, characterized by light absorption and scattering, frequently result in color distortion and low contrast in captured images. Current deep learning-based methods (like CNNs and Transformers) have advanced underwater image enhancement, yet window-based partitioning of standard Transformers limits non-local interaction modeling for efficiency. In this paper, we present a novel window-partitioning strategy dubbed downsampling shuffle, enabling the local window Transformer to capture non-local interactions. By pixel-spaced downsampling of original features, the partitioned window retains a near-global receptive field, allowing local window selfattention to model non-local interactions without extra computation costs. The resulting Transformer dubbed DSFormer efficiently processes images while maintaining a global receptive field, which is crucial for underwater image enhancement. Extensive experiments are conducted to verify the superiority of our DSFormer across public datasets.

Animation line inbetweening is a crucial step in animation production aimed at enhancing animation fluidity by predicting intermediate line arts between two key frames. However, existing methods face challenges in effectively addressing sparse pixels and significant motion in line art key frames. In literature, Chamfer Distance (CD) is commonly adopted for evaluating inbetweening performance. Despite achieving favorable CD values, existing methods often generate interpolated frames with line disconnections, especially for scenarios involving large motion. Motivated by this observation, we propose a simple yet effective interpolation method for animation line inbetweening that adopts thin-plate spline-based transformation to estimate coarse motion more accurately by modeling the keypoint correspondence between two key frames, particularly for large motion scenarios. Building upon the coarse estimation, a motion refine module is employed to further enhance motion details before final frame interpolation using a simple UNet model. Furthermore, to more accurately assess the performance of animation line inbetweening, we refine the CD metric and introduce a novel metric termed Weighted Chamfer Distance, which demonstrates a higher consistency with visual perception quality. Additionally, we incorporate Earth Mover's Distance and conduct user study to provide a more comprehensive evaluation. Our method outperforms existing approaches by delivering high-quality interpolation results with enhanced fluidity.

Generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input. Although remarkable progress has been made in video generation models, generative inbetweening still faces challenges in maintaining temporal stability due to the ambiguous interpolation path between two key frames. This issue becomes particularly severe when there is a large motion gap between input frames. In this paper, we propose a straight-forward yet highly effective Frame-wise Conditions-driven Video Generation (FCVG) method that significantly enhances the temporal stability of interpolated video frames. Specifically, our FCVG provides an explicit condition for each frame, making it much easier to identify the interpolation path between two input frames and thus ensuring temporally stable production of visually plausible video frames. To achieve this, we suggest extracting matched lines from two input frames that can then be easily interpolated frame by frame, serving as frame-wise conditions seamlessly integrated into existing video generation models. In extensive evaluations covering diverse scenarios such as natural landscapes, complex human poses, camera movements and animations, existing methods often exhibit incoherent transitions across frames. In contrast, our FCVG demonstrates the capability to generate temporally stable videos using both linear and non-linear interpolation curves. Our project page and code are available at https://fcvg-inbetween.github.io/.

Lens flare artifacts often emerge when capturing images under light sources due to the reflection and scattering of light. While existing methods primarily focus on data synthesis and collection schemes, there is a lack of specific architecture designed for this task. In this paper, we propose a RWKV-based network architecture suitable for flare removal. Firstly, we introduce a lightweight flare detection network to guide subsequent flare removal processes. Subsequently, we present a restoration network based on RWKV that efficiently captures global dependencies with linear computational complexity. Furthermore, we analyze the significance of two key modules within RWKV for this task, i.e., the attention mechanism and the token shift mechanism. We carefully select and integrate these mechanisms with minor adjustments specifically tailored for flare removal purposes. Our method demonstrates favorable performance across different datasets, particularly on real-world scenarios.

Recently, remarkable progress has been made in large-scale pre-trained model tuning, and inference efficiency is becoming more crucial for practical deployment. Early exiting in conjunction with multi-stage predictors, when cooperated with a parameter-efficient fine-tuning strategy, offers a straightforward way to achieve an inference-efficient model. However, a key challenge remains unresolved: How can early stages provide low-level fundamental features to deep stages while simultaneously supplying high-level discriminative features to early-stage predictors? To address this problem, we propose a Decoupled Multi-Predictor Optimization (DMPO) method to effectively decouple the low-level representative ability and high-level discriminative ability in early stages. First, in terms of architecture, we introduce a lightweight bypass module into multi-stage predictors for functional decomposition of shallow features from early stages, while a high-order statistics-based predictor is developed for early stages to effectively enhance their discriminative ability. To reasonably train our multi-predictor architecture, a decoupled optimization is proposed to allocate two-phase loss weights for multi-stage predictors during model tuning, where the initial training phase enables the model to prioritize the acquisition of discriminative ability of deep stages via emphasizing representative ability of early stages, and the latter training phase drives discriminative ability towards earlier stages as much as possible. As such, our DMPO can effectively decouple representative and discriminative abilities in early stages in terms of architecture design and model optimization. Experiments across various datasets and pre-trained backbones demonstrate that DMPO clearly outperforms its counterparts when reducing computational cost.

Multi-modal image fusion aims to integrate complementary information from different modalities to enhance perceptual capabilities in applications such as rescue and security. However, real-world imaging often suffers from degradation issues, such as noise, blur, and haze in visible imaging, as well as stripe noise in infrared imaging, which significantly degrades model performance. To address these challenges, we propose a task-gated multi-expert collaboration network (TG-ECNet) for degraded multi-modal image fusion. The core of our model lies in the task-aware gating and multi-expert collaborative framework, where the task-aware gating operates in two stages: degradation-aware gating dynamically allocates expert groups for restoration based on degradation types, and fusion-aware gating guides feature integration across modalities to balance information retention between fusion and restoration tasks. To achieve this, we design a two-stage training strategy that unifies the learning of restoration and fusion tasks. This strategy resolves the inherent conflict in information processing between the two tasks, enabling all-in-one multi-modal image restoration and fusion. Experimental results demonstrate that TG-ECNet significantly enhances fusion performance under diverse complex degradation conditions and improves robustness in downstream applications. The code is available at https://github.com/LeeX54946/TG-ECNet.

Image deblurring plays a crucial role in enhancing visual clarity across various applications. Although most deep learning approaches primarily focus on sRGB images, which inherently lose critical information during the image signal processing pipeline, RAW images, being unprocessed and linear, possess superior restoration potential but remain underexplored. Deblurring RAW images presents unique challenges, particularly in handling frequency-dependent blur while maintaining computational efficiency. To address these issues, we propose Frequency Enhanced Network (FrENet), a framework specifically designed for RAW-to-RAW deblurring that operates directly in the frequency domain. We introduce a novel Adaptive Frequency Positional Modulation module, which dynamically adjusts frequency components according to their spectral positions, thereby enabling precise control over the deblurring process. Additionally, frequency domain skip connections are adopted to further preserve high-frequency details. Experimental results demonstrate that FrENet surpasses state-of-the-art deblurring methods in RAW image deblurring, achieving significantly better restoration quality while maintaining high efficiency in terms of reduced MACs. Furthermore, FrENet's adaptability enables it to be extended to sRGB images, where it delivers comparable or superior performance compared to methods specifically designed for sRGB data. The source code will be publicly available.

Virtual furniture synthesis, a critical task in image composition, aims to seamlessly integrate reference objects into indoor scenes while preserving geometric coherence and visual realism. Despite its significant potential in home design applications, this field remains underexplored due to two major challenges: the absence of publicly available and ready-to-use benchmarks hinders reproducible research, and existing image composition methods fail to meet the stringent fidelity requirements for realistic furniture placement. To address these issues, we introduce RoomBench, a ready-to-use benchmark dataset for virtual furniture synthesis, comprising 7,298 training pairs and 895 testing samples across 27 furniture categories. Then, we propose RoomEditor, a simple yet effective image composition method that employs a parameter-sharing dual U-Net architecture, ensuring better feature consistency by sharing weights between dual branches. Technical analysis reveals that conventional dual-branch architectures generally suffer from inconsistent intermediate features due to independent processing of reference and background images. In contrast, RoomEditor enforces unified feature learning through shared parameters, thereby facilitating model optimization for robust geometric alignment and maintaining visual consistency. Experiments show our RoomEditor is superior to state-of-the-arts, while generalizing directly to diverse objects synthesis in unseen scenes without task-specific fine-tuning. Our dataset and code are available at https://github.com/stonecutter-21/roomeditor.

Omnidirectional images have attracted significant attention in recent years due to the rapid development of virtual reality technologies. Equirectangular projection (ERP), a naive form to store and transfer omnidirectional images, however, is challenging for existing two-dimensional (2D) image super-resolution (SR) methods due to its inhomogeneous distributed sampling density and distortion across latitude. In this paper, we make one of the first attempts to design a spherical pseudo-cylindrical representation, which not only allows pixels at different latitudes to adaptively adopt the best distinct sampling density but also is model-agnostic to most off-the-shelf SR methods, enhancing their performances. Specifically, we start by upsampling each latitude of the input ERP image and design a computationally tractable optimization algorithm to adaptively obtain a (sub)-optimal sampling density for each latitude of the ERP image. Addressing the distortion of ERP, we introduce a new viewport-based training loss based on the original 3D sphere format of the omnidirectional image, which inherently lacks distortion. Finally, we present a simple yet effective recursive progressive omnidirectional SR network to showcase the feasibility of our idea. The experimental results on public datasets demonstrate the effectiveness of the proposed method as well as the consistently superior performance of our method over most state-of-the-art methods both quantitatively and qualitatively.

In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration. In particular, We ingeniously embed an image-to-text mapper and text restoration module into CLIP-equipped text-to-image models to generate the guidance. Then, we adopt a simple coarse-to-fine approach to dynamically inject multi-scale information from guidance to image restoration networks. Extensive experiments are conducted on various image restoration tasks, including deblurring, dehazing, deraining, and denoising, and all-in-one image restoration. The results showcase that our method outperforms state-of-the-art ones across all these tasks. The codes and models are available at https://github.com/mrluin/TextualDegRemoval.

Cross-domain face translation aims to transfer face images from one domain to another. It can be widely used in practical applications, such as photos/sketches in law enforcement, photos/drawings in digital entertainment, and near-infrared (NIR)/visible (VIS) images in security access control. Restricted by limited cross-domain face image pairs, the existing methods usually yield structural deformation or identity ambiguity, which leads to poor perceptual appearance. To address this challenge, we propose a multi-view knowledge (structural knowledge and identity knowledge) ensemble framework with frequency consistency (MvKE-FC) for cross-domain face translation. Due to the structural consistency of facial components, the multi-view knowledge learned from large-scale data can be appropriately transferred to limited cross-domain image pairs and significantly improve the generative performance. To better fuse multi-view knowledge, we further design an attention-based knowledge aggregation module that integrates useful information, and we also develop a frequency-consistent (FC) loss that constrains the generated images in the frequency domain. The designed FC loss consists of a multidirection Prewitt (mPrewitt) loss for high-frequency consistency and a Gaussian blur loss for low-frequency consistency. Furthermore, our FC loss can be flexibly applied to other generative models to enhance their overall performance. Extensive experiments on multiple cross-domain face datasets demonstrate the superiority of our method over state-of-the-art methods both qualitatively and quantitatively.

By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset, misalignment is inevitable between training pairs, making existing methods possibly suffer from deformation artifacts. In this paper, we propose a joint deblurring and reblurring learning (JDRL) framework for single image defocus deblurring with misaligned training pairs. Generally, JDRL consists of a deblurring module and a spatially invariant reblurring module, by which deblurred result can be adaptively supervised by ground-truth image to recover sharp textures while maintaining spatial consistency with the blurry image. First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images. Second, in the reblurring module, deblurred result is reblurred to be spatially aligned with blurry image, by predicting a set of isotropic blur kernels and weighting maps. Moreover, we establish a new single image defocus deblurring (SDD) dataset, further validating our JDRL and also benefiting future research. Our JDRL can be applied to boost defocus deblurring networks in terms of both quantitative metrics and visual quality on DPDD, RealDOF and our SDD datasets.

Natural videos captured by consumer cameras often suffer from low framerate and motion blur due to the combination of dynamic scene complexity, lens and sensor imperfection, and less than ideal exposure setting. As a result, computational methods that jointly perform video frame interpolation and deblurring begin to emerge with the unrealistic assumption that the exposure time is known and fixed. In this work, we aim ambitiously for a more realistic and challenging task - joint video multi-frame interpolation and deblurring under unknown exposure time. Toward this goal, we first adopt a variant of supervised contrastive learning to construct an exposure-aware representation from input blurred frames. We then train two U-Nets for intramotion and inter-motion analysis, respectively, adapting to the learned exposure representation via gain tuning. We finally build our video reconstruction network upon the exposure and motion representation by progressive exposureadaptive convolution and motion refinement. Extensive experiments on both simulated and real-world datasets show that our optimized method achieves notable performance gains over the state-of-the-art on the joint video ×8 interpolation and deblurring task. Moreover, on the seemingly implausible ×16 interpolation task, our method outperforms existing methods by more than 1.5 dB in terms of PSNR.

Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row, yielding RS distortions for dynamic scenes. To correct RS distortions, existing methods adopt a fully supervised learning manner, where high framerate global shutter (GS) images should be collected as ground-truth supervision. In this paper, we propose a Self-supervised learning framework for Dual reversed RS distortions Correction (SelfDRSC), where a DRSC network can be learned to generate a high framerate GS video only based on dual RS images with reversed distortions. In particular, a bidirectional distortion warping module is proposed for reconstructing dual reversed RS images, and then a self-supervised loss can be deployed to train DRSC network by enhancing the cycle consistency between input and reconstructed dual reversed RS images. Besides start and end RS scanning time, GS images at arbitrary intermediate scanning time can also be supervised in SelfDRSC, thus enabling the learned DRSC network to generate a high framerate GS video. Moreover, a simple yet effective self-distillation strategy is introduced in self-supervised loss for mitigating boundary artifacts in generated GS images. On synthetic dataset, SelfDRSC achieves better or comparable quantitative metrics in comparison to state-of-the-art methods trained in the full supervision manner. On real-world RS cases, our SelfDRSC can produce high framerate GS videos with finer correction textures and better temporary consistency. The source code and trained models are made publicly available at https://github.com/shangwei5/SelfDRSC.

Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether logit mimicking always lags behind feature imitation. Towards this goal, we first present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Second, we introduce the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking under-performs for years. The thorough studies exhibit the great potential of logit mimicking that can significantly alleviate the localization ambiguity, learn robust feature representation, and ease the training difficulty in the early stage. We also provide the theoretical connection between the proposed LD and the classification KD, that they share the equivalent optimization effect. Our distillation scheme is simple as well as effective and can be easily applied to both dense horizontal object detectors and rotated object detectors. Extensive experiments on the MS COCO, PASCAL VOC, and DOTA benchmarks demonstrate that our method can achieve considerable AP improvement without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.

Recently, deep learning-based crowd counting methods have achieved promising performance on test data with the same distribution as training set, while performance degradation usually occurs when testing on other or unseen domains. Due to the variations in scene contexts, crowd densities and head scales, it is a very challenging issue to tackle multi-domain crowd counting using one deep model. In this work, we propose a domain-guided channel attention network (DCANet) towards learning multi-domain crowd counting. In particular, our DCANet consists of feature extraction module, channel attention-guided multi-dilation (CAMD) module and density map prediction module. Given a testing image from a certain domain, channel attention is adopted to guide the extraction of domain-specific feature representation, and thus our DCANet can adaptively handle images from multiple domains. We further propose two domain-guided learning strategies, i.e., dataset-level domain kernel (DDK) supervision and image-level domain kernel (IDK) supervision, by which channel attention in CAMD can be explicitly optimized to emphasize the channels corresponding to the domain of an input image. Furthermore, IDK can be adaptively updated when training DCANet, thereby improving the generalization ability to unseen scenes. Experimental results on benchmark datasets show that our DCANet performs favorably for handling multi-domain datasets using one single model. Moreover, our IDK training strategy can be applied to boost state-of-the-art methods on single domain dataset.

Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ. The source code and model are available at https://github.com/happycaoyue/JSPL.

Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement. In this paper, by reformulating the knowledge distillation process on localization, we present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Moreover, we also heuristically introduce the concept of valuable localization region that can aid to selectively distill the semantic and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and localization knowledge distillation is more important and efficient than semantic knowledge for distilling object detectors. Our distillation scheme is simple as well as effective and can be easily applied to different dense object detectors. Experiments show that our LD can boost the AP score of GFocal-ResNet-50 with a single-scale 1 x training schedule from 40.1 to 42.1 on the COCO benchmark without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.

Existing image restoration methods usually assume specific degradation model, e.g., linear combination of clean image and degradation map in image denoising and deraining. Benefiting from the power of deep learning, a restoration mapping can be learned from degraded image to latent clean image. In this paper, we propose to integrate degradation learning into image restoration (IDLIR), where degradation model can be learned from training samples. In particular, IDLIR is an iterative restoration framework, where latent clean image and degradation map can be extracted from current residual degraded image, and are then fused by a degradation network to reconstruct degraded image. Then the residual degradation image can be updated by computing the difference between input and reconstructed degraded images. By taking denoising and deraining as examples, IDLIR is compared with state-of-the-art methods on several benchmark datasets. IDLIR performs better than state-of-the-art methods quantitatively and qualitatively.

Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world rainy images. Although semi-supervised methods are suggested to exploit real-world rainy images when training deep deraining models, their performances are still notably inferior. To address this crucial issue, this work proposes a semi-supervised image deraining network with knowledge distillation (SSID-KD) for better exploiting real-world rainy images. In particular, the consistency of feature distribution of rain streaks extracted from synthetic and real-world rainy images is enforced by adopting knowledge distillation. Moreover, as for the backbone in SSID-KD, we propose the multi-scale feature fusion module and the pyramid fusion module to better extract deep features of rainy images. SSID-KD can relieve the problem of over-deraining or under-deraining for real-world rainy images, while it can keep comparable performance with supervised deraining methods on several benchmark datasets. Extensive experiments on both synthetic and real-world rainy images have validated that our SSID-KD not only can achieve better deraining results than existing semi-supervised deraining methods but also are quantitatively comparable with state-of-the-art supervised deraining methods. Benefiting from the well exploration of real-world rainy images, our SSID-KD can obtain more visually plausible deraining results. The source code and trained models are publicly available athttps://github.com/cuiyixin555/SSID-KD.

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this article, we propose complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding-box regression and nonmaximum suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, that is: 1) overlap area; 2) normalized central-point distance; and 3) aspect ratio, which are crucial for measuring bounding-box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted$\ell _{n}$-norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires fewer iterations. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT and BlendMask-RT), and object detection (e.g., YOLO v3, SSD, and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR100for object detection, and +1.1 AP and +3.5 AR100for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available athttps://github.com/Zzh-tju/CIoU.

Recently, video deblurring has attracted considerable research attention, and several works suggest that events at high time rate can benefit deblurring. Existing video deblurring methods assume consecutively blurry frames, while neglecting the fact that sharp frames usually appear nearby blurry frame. In this paper, we develop a principled framework D2Nets for video deblurring to exploit non-consecutively blurry frames, and propose a flexible event fusion module (EFM) to bridge the gap between event-driven and video deblurring. In D2Nets, we propose to first detect nearest sharp frames (NSFs) using a bidirectional LST-M detector, and then perform deblurring guided by NSFs. Furthermore, the proposed EFM is flexible to be incorporated into D2Nets, in which events can be leveraged to notably boost the deblurring performance. EFM can also be easily incorporated into existing deblurring networks, making event-driven deblurring task benefit from state-of-the-art deblurring methods. On synthetic and real-world blurry datasets, our methods achieve better results than competing methods, and EFM not only benefits D2Nets but also significantly improves the competing deblurring networks.

Most existing non-blind restoration methods are based on the assumption that a precise degradation model is known. As the degradation process can only be partially known or inaccurately modeled, images may not be well restored. Rain streak removal and image deconvolution with inaccurate blur kernels are two representative examples of such tasks. For rain streak removal, although an input image can be decomposed into a scene layer and a rain streak layer, there exists no explicit formulation for modeling rain streaks and the composition with scene layer. For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well. In this paper, we propose a principled algorithm within the maximum a posterior framework to tackle image restoration with a partially known or inaccurate degradation model. Specifically, the residual caused by a partially known or inaccurate degradation model is spatially dependent and complexly distributed. With a training set of degraded and ground-truth image pairs, we parameterize and learn the fidelity term for a degradation model in a task-driven manner. Furthermore, the regularization term can also be learned along with the fidelity term, thereby forming a simultaneous fidelity and regularization learning model. Extensive experimental results demonstrate the effectiveness of the proposed model for image deconvolution with inaccurate blur kernels, deconvolution with multiple degradations and rain streak removal.

Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. Furthermore, this paper summarizes three geometric factors in bounding box regression, i.e., overlap area, central point distance and aspect ratio, based on which a Complete IoU (CIoU) loss is proposed, thereby leading to faster convergence and better performance. By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e.g., YOLO v3, SSD and Faster R-CNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric. Moreover, DIoU can be easily adopted into non-maximum suppression (NMS) to act as the criterion, further boosting performance improvement. The source code and trained models are available at https://github.com/Zzh-tju/DIoU.

In many real-world face restoration applications, e.g., smartphone photo albums and old films, multiple high-quality (HQ) images of the same person usually are available for a given degraded low-quality (LQ) observation. However, most existing guided face restoration methods are based on single HQ exemplar image, and are limited in properly exploiting guidance for improving the generalization ability to unknown degradation process. To address these issues, this paper suggests to enhance blind face restoration performance by utilizing multi-exemplar images and adaptive fusion of features from guidance and degraded images. First, given a degraded observation, we select the optimal guidance based on the weighted affine distance on landmark sets, where the landmark weights are learned to make the guidance image optimized to HQ image reconstruction. Second, moving least-square and adaptive instance normalization are leveraged for {spatial} alignment and illumination translation of guidance image in the feature space. Finally, for better feature fusion, multiple adaptive spatial feature fusion (ASFF) layers are introduced to incorporate guidance features in an adaptive and progressive manner, resulting in our ASFFNet. Experiments show that our ASFFNet performs favorably in terms of quantitative and qualitative evaluation, and is effective in generating photo-realistic results on real-world LQ images. The source code and models are available at https://github.com/csxmli2016/ASFFNet.

Blind deconvolution is a classical yet challenging low-level vision problem with many real-world applications. Traditional maximum a posterior (MAP) based methods rely heavily on fixed and handcrafted priors that certainly are insufficient in characterizing clean images and blur kernels, and usually adopt specially designed alternating minimization to avoid trivial solution. In contrast, existing deep motion deblurring networks learn from massive training images the mapping to clean image or blur kernel, but are limited in handling various complex and large size blur kernels. To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution. In particular, we adopt an asymmetric Autoencoder with skip connections for generating latent clean image, and a fully-connected network (FCN) for generating blur kernel. Moreover, the SoftMax nonlinearity is applied to the output layer of FCN to meet the non-negative and equality constraints. The process of neural optimization can be explained as a kind of ''zero-shot" self-supervised learning of the generative networks, and thus our proposed method is dubbed SelfDeblur. Experimental results show that our SelfDeblur can achieve notable quantitative gains as well as more visually plausible deblurring results in comparison to state-of-the-art blind deconvolution methods on benchmark datasets and real-world blurry images. The source code is publicly available at https://github.com/csdwren/SelfDeblur.

Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task. Despite considerable advance, the reasons on effectiveness of GCP on deep CNNs have not been well studied. In this paper, we make an attempt to understand what deep CNNs benefit from GCP in a viewpoint of optimization. Specifically, we explore the effect of GCP on deep CNNs in terms of the Lipschitzness of optimization loss and the predictiveness of gradients, and show that GCP can make the optimization landscape more smooth and the gradients more predictive. Furthermore, we discuss the connection between GCP and second-order optimization for deep CNNs. More importantly, above findings can account for several merits of covariance pooling for training deep CNNs that have not been recognized previously or fully explored, including significant acceleration of network convergence (i.e., the networks trained with GCP can support rapid decay of learning rates, achieving favorable performance while significantly reducing number of training epochs), stronger robustness to distorted examples generated by image corruptions and perturbations, and good generalization ability to different vision tasks, e.g., object detection and instance segmentation. We conduct extensive experiments using various deep CNN architectures on diversified tasks, and the results provide strong support to our findings.

Single image deraining has been widely studied in recent years. Motivated by residual learning, most deep learning based deraining approaches devote research attention to extracting rain streaks, usually yielding visual artifacts in final deraining images. To address this issue, we in this paper propose bilateral recurrent network (BRN) to simultaneously exploit rain streak layer and background image layer. Generally, we employ dual residual networks (ResNet) that are recursively unfolded to sequentially extract rain streaks and predict clean background image. Furthermore, we propose bilateral LSTMs into dual ResNets, which not only can respectively propagate deep features across multiple stages, but also bring the interplay between rain streak layer and background image layer. The experimental results demonstrate that our BRN notably outperforms state-of-the-art deep deraining networks on both synthetic datasets and real rainy images. All the source code and pre-trained models are available at https://github.com/shangwei5/BRN.

Single image deraining has received considerable progress based on deep convolutional neural network (CNN). In existing deep deraining methods, CNNs are deployed to extract rain streaks while failing in learning direct mapping from rainy image to clean background image, and their architectures become more and more complicated. In this work, we first propose a single recurrent network (SRN) by recursively unfolding a shallow residual network, where a recurrent layer is adopted to propagate deep features across multiple stages. This simple SRN is effective not only in learning residual mapping for extracting rain streaks, but also in learning direct mapping for predicting clean background image. Furthermore, two SRNs are coupled to simultaneously exploit rain streak layer and clean background image layer. Instead of naive combination, we propose bilateral LSTMs, which not only can respectively propagate deep features of rain streak layer and background image layer across stages, but also bring the interplay between these two SRNs, finally forming bilateral recurrent network (BRN). The experimental results demonstrate that our BRN notably outperforms state-of-the-art deep deraining networks on synthetic datasets quantitatively and qualitatively. The proposed methods also perform more favorably in terms of generalization performance on real-world rainy dataset. All the source code and pre-trained models are available at https://github.com/csdwren/RecDerain.

Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent γ) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with γ > 1, while the texture map is generated by been shrank with γ < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents γ. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.

Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with unsubstantial degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of residual image. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at https://github.com/csdwren/PReNet.

Recent years have witnessed the great progress on deep image deraining networks. On the one hand, deraining performance has been significantly improved by designing complex network architectures, yielding high computational cost. On the other hand, several lightweight networks try to improve computational efficiency, but at the cost of notable degrading deraining performance. In this paper, we propose a dual recursive network (DRN) for fast image deraining as well as comparable or superior deraining performance compared with state-of-the-art approaches. Specifically, our DRN utilizes a residual network (ResNet) with only 2 residual blocks (ResBlock), which is recursively unfolded to remove rain streaks in multiple stages. Meanwhile, the 2 ResBlocks can be recursively computed in one stage, forming the dual recursive network. Experimental results show that DRN is very computationally efficient and can achieve favorable deraining results on both synthetic and real rainy images. The source codes and pre-trained models are available at https://github.com/csdwren/DRN.

Most blind deconvolution methods usually pre-define a large kernel size to guarantee the support domain. Blur kernel estimation error is likely to be introduced, yielding severe artifacts in deblurring results. In this paper, we first theoretically and experimentally analyze the mechanism to estimation error in oversized kernel, and show that it holds even on blurry images without noises. Then to suppress this adverse effect, we propose a low rank-based regularization on blur kernel to exploit the structural information in degraded kernels, by which larger-kernel effect can be effectively suppressed. And we propose an efficient optimization algorithm to solve it. Experimental results on benchmark datasets show that the proposed method is comparable with the state-of-the-arts by accordingly setting proper kernel size, and performs much better in handling larger-size kernels quantitatively and qualitatively. The deblurring results on real-world blurry images further validate the effectiveness of the proposed method.

Most non-blind deconvolution methods are developed under the error-free kernel assumption, and are not robust to inaccurate blur kernel. Unfortunately, despite the great progress in blind deconvolution, estimation error remains inevitable during blur kernel estimation. Consequently, severe artifacts such as ringing effects and distortions are likely to be introduced in the non-blind deconvolution stage. In this paper, we tackle this issue by suggesting: 1) a partial map in the Fourier domain for modeling kernel estimation error, and 2) a partial deconvolution model for robust deblurring with inaccurate blur kernel. The partial map is constructed by detecting the reliable Fourier entries of estimated blur kernel. And partial deconvolution is applied to wavelet-based and learning-based models to suppress the adverse effect of kernel estimation error. Furthermore, an E-M algorithm is developed for estimating the partial map and recovering the latent sharp image alternatively. Experimental results show that our partial deconvolution model is effective in relieving artifacts caused by inaccurate blur kernel, and can achieve favorable deblurring quality on synthetic and real blurry images.

Salient edge selection and time-varying regularization are two crucial techniques to guarantee the success of maximum a posteriori (MAP)-based blind deconvolution. However, the existing approaches usually rely on carefully designed regularizers and handcrafted parameter tuning to obtain satisfactory estimation of the blur kernel. Many regularizers exhibit the structure-preserving smoothing capability, but fail to enhance salient edges. In this paper, under the MAP framework, we propose the iteration-wise ℓp-norm regularizers together with data-driven strategy to address these issues. First, we extend the generalized shrinkage-thresholding (GST) operator for ℓp-norm minimization with negative p value, which can sharpen salient edges while suppressing trivial details. Then, the iteration-wise GST parameters are specified to allow dynamical salient edge selection and time-varying regularization. Finally, instead of handcrafted tuning, a principled discriminative learning approach is proposed to learn the iterationwise GST operators from the training dataset. Furthermore, the multi-scale scheme is developed to improve the efficiency of the algorithm. Experimental results show that, negative p value is more effective in estimating the coarse shape of blur kernel at the early stage, and the learned GST operators can be well generalized to other dataset and real world blurry images. Compared with the state-of-the-art methods, our method achieves better deblurring results in terms of both quantitative metrics and visual quality, and it is much faster than the state-of-the-art patch-based blind deconvolution method.

The maximum a posterior (MAP)-based blind deconvolution framework generally involves two stages: blur kernel estimation and non-blind restoration. For blur kernel estimation, sharp edge prediction and carefully designed image priors are vital to the success of MAP. In this paper, we propose a blind deconvolution framework together with iteration specific priors for better blur kernel estimation. The family of hyper-Laplacian (Pr(d) ∝ e-∥d∥pp/λ) is adopted for modeling iteration-wise priors of image gra- dients, where each iteration has its own model parameters {λ(t), p(t)}. To avoid heavy parameter tuning, all iteration-wise model parameters can be learned using our principled discriminative learning model from a training set, and can be directly applied to other dataset and real blurry images. Interestingly, with the generalized shrinkage / thresholding operator, negative p value (p <;0) is allowable and we find that it contributes more in estimating the coarse shape of blur kernel. Experimental results on synthetic and real world images demonstrate that our method achieves better deblurring results than the existing gradient prior-based methods. Compared with the state-of-the-art patch prior-based method, our method is competitive in restoration results but is much more efficient.