Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Ming–Hsuan YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works234 from public data
- An Underwater Image Enhancement Benchmark Dataset and Beyond2,389
This paper constructs an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images and proposes an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs).
- Benchmarking Single-Image Dehazing and Beyond2,349
This work presents a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE), which highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes.
- Single Image Dehazing via Multi-scale Convolutional Neural Networks1,809
A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
- Gated Fusion Network for Single Image Dehazing953
An efficient algorithm to directly restore a clear image from a hazy input using an end-to-end trainable neural network that consists of an encoder and a decoder is proposed.
- Single Image Super-Resolution via a Holistic Attention Network857
A new holistic attention network (HAN) is proposed, which consists of a layer attention module (LAM) and a channel-spatial attention Module (CSAM) to model the holistic interdependencies among layers, channels, and positions.
- 600
- 522
- Domain Adaptation for Image Dehazing477
This work proposes a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules, and applies a bidirectional translation network to bridge the gap between the synthetic and real domains by translating images from one domain to another.
- Deep Image Deblurring: A Survey415
This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review.
- Omni-Kernel Network for Image Restoration412
An efficient convolutional network for image restoration by enhancing multi-scale representation learning using an omni-kernel module that consists of three branches, i.e., global, large, and local branches, to learn global-to-local feature representations efficiently.
- Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges387
A multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines dehazed results locally.
- 376
- Single Image Deraining: A Comprehensive Benchmark Analysis371
A comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images, and provides a rich variety of criteria for dehazing algorithm evaluation.
- Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study351
The UG2+ challenge Track 2 competition in IEEE CVPR 2019 is launched, aiming to evoke a comprehensive discussion and exploration about whether and how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios.
- 296
- 281
- 281
- Logit Standardization in Knowledge Distillation271
The proposed Z-score pre-process enables student to focus on essential logit relations from teacher rather than requiring a magnitude match, and can improve the performance of existing logit-based distillation methods.
- 260
- 243
- 240
- Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color Correction231
Experimental results show that the novel method for underwater image restoration outperforms state-of-the-art methods, demonstrating its efficacy in dealing with uneven lighting and diverse underwater environments.
- 230
- 226
- Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better220
A new end-to-end video deraining framework, dubbed Enhanced Spatio-Temporal Interaction Network (ESTINet), which considerably boosts current state-of-the-art video derained quality and speed and takes the advantage of deep residual networks and convolutional long short-term memory.
- 219
- 216
- MC-Blur: A Comprehensive Benchmark for Image Deblurring188
This paper constructs a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors, and conducts extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity.
- Restoring Images in Adverse Weather Conditions via Histogram Transformer186
This work proposes an efficient Histogram Transformer (Histoformer) for restoring images affected by adverse weather powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins and presents a dynamic-range convolution enabling conventional convolution to conduct operation over similar pixels rather than neighbor pixels.
- 153
- NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer143
Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of the NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.
- 133
- A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning117
This article provides a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing, and discusses the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used.
- 115
- 114
- 112
- RESIDE: A Benchmark for Single Image Dehazing.110
This paper presents a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE), and provides a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metric, to subjective evaluation and the novel task-driven evaluation.
- 107
- Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel105
This paper analyzes the relationship between motion blur trajectory and optical flow, and presents a novel pixel-wise non-linear kernel model to account for motion blur, which describes complex motion blur more effectively.
- LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment104
This paper proposes the framework of Local and Global Pyramid Mask Alignment, which adopts the soft pyramid mask learning mechanism in both the local and global feature maps and allows the predicted boundaries of bounding boxes to break through the limitation of original proposals.
- DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation103
This work proposes a novel Densely Connected NAS framework, which directly searches the optimal network structures for the multi-scale representations of visual information, over a large-scale target dataset without proxy, and introduces a densely connected search space to cover an abundance of mainstream network designs.
- 99
- 99
- 97
- 97
- Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation96
The authors' analysis shows that the estimated decomposed matrices contain the most essential information of the input kernel, which ensures the proposed network to handle various blurs in a unified framework and generate high-quality deblurring results.
- 94
- Memory-Augmented Deep Unfolding Network for Guided Image Super-resolution93
A maximum a posteriori (MAP) estimation model for GISR with two types of priors on the HR target image, i.e., local implicit prior and global implicit prior is proposed, and a novel alternating optimization algorithm is designed to solve this model.
- ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring92
Quantitative and qualitative experiments show that the proposed implicit method to learn spatial correspondence among blurry frames in the feature space performs favorably on both datasets against previous state-of-the-art methods, confirming the benefit of modeling all-range spatial correspondence for video deblurring.
- Face Super-Resolution Guided by 3D Facial Priors89
This paper proposes a novel face super-resolution method that explicitly incorporates 3D facial priors which grasp the sharp facial structures and is the first to explore 3D morphable knowledge based on the fusion of parametric descriptions of face attributes.
- Joint learning of image detail and transmission map for single image dehazing87
A new deep learning-based method for removing haze from single input image is proposed via joint estimation of clear image detail and transmission map, which is different from traditional methods only estimating a transmission map for a hazy image.
- 86
- SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing86
A novel self-paced semi-curricular attention network, called SCANet, for non-homogeneous image dehazing that focuses on enhancing haze-occluded regions that outperforms many state-of-the-art methods.
- Learning to Deblur Images with Exemplars84
This paper proposes a deblurring algorithm based on an exemplar dataset without using coarse-to-fine strategies or heuristic edge selections, and develops a convolutional neural network to restore sharp edges from blurry images fordeblurring.
- Single image rain removal via a deep decomposition–composition network83
A novel multi-task leaning architecture in an end-to-end manner to reduce the mapping range from input to output and boost the performance, and is applicable to other layer decomposition tasks like dust removal.
- Dual-Domain Attention for Image Deblurring82
This study develops the dual-domain attention mechanism for image deblurring by implementing self-attention in the style of dynamic group convolution for integrating information from the local region, enhancing the representation learning capability and reducing computational burden.
- 81
- Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors78
This work introduced a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods and tailor a novel training pipeline by introducing an online negative sample generation strategy.
- Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior78
A Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information is presented, and a Semantic-Aware Deraining Module (SADM) is developed which solves both tasks of semantic segmentation and deraining of scenes.
- Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview77
This paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmentation circumstances.
- A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives71
A comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images of various rain types, which indicates the gap between the achievable performance on synthetic rainy images and the practical demand on real-world images.
- 70
- 67
- 67
- 67
- 65
- Patch is enough: naturalistic adversarial patch against vision-language pre-training models61
Evaluated LVLMs demonstrate limited proficiency not only in specialized tasks but also in general tasks, including object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning.
- 59
- 59
- 59
- NLDN: Non-local dehazing network for dense haze removal58
A Non-local Dehazing Network (NLDN), which learns the mapping between hazy images and haze-free images, and performs favorably against other state-of-the-art methods on both synthetic dataset and real-world images.
- 56
- Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding55
A Paired Rain Removal Network (PRRNet) is presented, which exploits both stereo images and semantic information, and a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively.
- 54
- 54
- Underwater image restoration via depth map and illumination estimation based on a single image48
A dehazing method utilizing the revised model, which depends on the scene depth map and a color correction method to eliminate color distortion and can be applied to various real-world underwater scenes and has better contrast and color.
- Anisotropic second and fourth order diffusion models based on Convolutional Virtual Electric Field for image denoising48
The proposed CONVEF-based Y-K model is an anisotropic diffusion equation which can avoid the over-smoothness of edges and provide better edge protection capability except for better denoising.
- 46
- 46
- 46
- 46
- Self-supervised Learning and Adaptation for Single Image Dehazing45
Under the depth guidance estimated by a well-trained depth estimation network, the conventional atmospheric scattering model is used to generate massive hazy-clean image pairs for the self-supervised pre-training of dehazing network and self- supervised adaptation is presented to adapt pre-trained network to real hazy images.
- 45
- Clustering-Induced Adaptive Structure Enhancing Network for Incomplete Multi-View Data44
A Clustering-induced Adaptive Structure Enhancing Network (CASEN) for incomplete multi-view clustering is proposed, which is an end-to-end trainable framework that jointly conducts multi-view structure enhancing and data clustering.
- A Comprehensive Survey on Image Dehazing Based on Deep Learning43
A comprehensive survey on the recent proposed dehazing methods concludes the commonly used datasets, loss functions and evaluation metrics and group the existing researches into two major categories: supervised ID and unsupervised ID.
- 42
- Pyramid Architecture Search for Real-Time Image Deblurring42
A novel deblurring method, dubbed PyNAS (pyramid neural architecture search network), towards automatically designing hyper-parameters including the scales, patches, and standard cell operators, and uses a path-level binarization mechanism for multi-scale cell searching to save the memory consumption.
- 41
- 41
- 41
- An efficient privacy protection scheme for data security in video surveillance40
A novel and efficient privacy protection scheme for data security in video surveillance, which jointly addresses several key challenges, including de-identification, behavior preservation, recoverability, and compressibility in one unified system is proposed.
- A Hybrid Transformer-Mamba Network for Single Image Deraining39
A novel dual-branch hybrid Transformer-Mamba network, denoted as TransMamba, aimed at effectively capturing long-range rain-related dependencies and developing a spectral coherence loss to better reconstruct innate signal-level relations within clean images.
- 38
- 37
- Autonomous underwater robot for underwater image enhancement via multi-scale deformable convolution network with attention mechanism36
A multi-scale deformable convolutional network with an attention mechanism (MsDCANet) to enhance the quality of underwater images and improve the performance of vision tasks and be applied to aquaculture development.
- 36
- 35
- Deep Correlated Predictive Subspace Learning for Incomplete Multi-View Semi-Supervised Classification35
The proposed Deep Correlated Predictive Subspace Learning (DCPSL) method is able to learn proper subspace representation that is suitable for class label prediction, which can further improve the performance of classification.
- 34
- Dual Prompting Image Restoration with Diffusion Transformers33
This paper introduces DPIR (Dual Prompting Image Restoration), a novel image restoration method that effectivly extracts conditional information of low-quality images from multiple perspectives and delivers superior image restoration performance.
- Rendering Portraitures from Monocular Camera and Beyond33
This work introduces an automatic system that achieves portrait DoF rendering for monocular cameras using Convolutional Neural Networks and trains a spatially-variant Recursive Neural Network to learn and accelerate this rendering process.
- 32
- 32
- 31
- 31
- Image denoising using anisotropic second and fourth order diffusions based on gradient vector convolution31
Novel second order and fourth order diffusion models are proposed for image denoising based on the gradient vector convolution (GVC) model, which has many advantages over traditional ones, such as low computational cost, high numerical stability and remarkableDenoising effect.
- 30
- 30
- 29
- 29
- 27
- DI-Retinex: Digital-Imaging Retinex Model for Low-Light Image Enhancement27
This paper proposes a new expression called Digital-Imaging Retinex model (DI-Retinex), which includes an offset term in the enhancement model, which allows for pixel-wise brightness contrast adjustment with a non-linear mapping function and design a variance suppression loss for regulating the additional offset term.
- 26
- 24
- Learning Hierarchical Dynamics with Spatial Adjacency for Image Enhancement24
A DCP-guided hierarchical dynamic mechanism for image enhancement to adapt the model parameters and features from local to global as well as to keep spatial adjacency within the region to achieve state-of-the-art performance and generates visually pleasing images.
- Every Moment Matters: Detail-Aware Networks to Bring a Blurry Image Alive24
A detail-aware network with three consecutive stages to improve the reconstruction quality by addressing specific aspects in the recovery process and produces sharp image sequences with rich details and subtle motion, outperforming the state-of-the-art methods.
- 24
- 23
- UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network23
UncTrack is a novel uncertainty-aware transformer-based tracker that predicts the target localization uncertainty and incorporates this uncertainty information for accurate target state inference and outperforms the state-of-the-art methods.
- RFFNet: Towards Robust and Flexible Fusion for Low-Light Image Denoising23
A multi-scale inconsistency calibration module to address inconsistency before fusion by first mapping the guidance features to multi-scale spaces and calibrating them with the aid of pre-denoising features in a coarse-to-fine manner is presented.
- 22
- 22
- Deep Video Dehazing22
This work develops a deep learning solution for video dehazing, where a CNN is trained end-to-end to learn how to accumulate information across frames for transmission estimation and is subsequently used to recover a haze-free frame via atmospheric scattering model.
- 21
- Omnidirectional Image Super-resolution via Bi-projection Fusion21
A novel Bi-Projection Omnidirectional Image Super-Resolution (BPOSR) network to take advantage of the geometric properties of the above two projections to achieve state-of-the-art performance on omnidirectional image super-resolution.
- 21
- 20
- Cylin-Painting: Seamless 360° Panoramic Image Outpainting and Beyond19
A deep analysis of the differences between inpainting and outpainting is provided, which essentially depends on how the source pixels contribute to the unknown regions under different spatial arrangements, and a learnable positional embedding strategy to incorporate the missing component of positional encoding into the cylinder convolution, which significantly improves the panoramic results.
- 19
- 19
- Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining18
A dual-branch spatiotemporal state-space model is proposed to enhance rain streak removal in video sequences and develops a median stacking loss to enable semi-supervised learning by generating pseudo-clean patches based on the sparsity prior of rain.
- 18
- Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection16
This paper proposes a new method named Environmental Matching Attack (EMA) to address the issue of optimizing the adversarial patch under the constraints of color, and is the first to consider natural patches in the domain of UAVs.
- 16
- Fast Ultra High-Definition Video Deblurring via Multi-scale Separable Network15
A novel deep model for fast and accurate UHD video deblurring (UHDVD) is proposed by a depth-wise separable-patch architecture, which operates with a multi-scale integration scheme to achieve a large receptive field without adding the number of generic convolutional layers and kernels.
- 15
- Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition15
This work excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost, and designs a two-branch reciprocal feature learning framework in order to adequately utilize the features from both the tasks.
- 14
- DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement13
A new expression called Digital-Imaging Retinex theory (DI-Retinex) is proposed through theoretical and experimental analysis of Retinex theory in digital imaging, which includes an offset term in the enhancement model, which allows for pixel-wise brightness contrast adjustment with a non-linear mapping function.
- 3D Priors-Guided Diffusion for Blind Face Restoration13
This work proposes a novel diffusion-based framework by embedding the 3D facial priors as structure and identity constraints into a denoising diffusion process, and proposes a Time-Aware Fusion Block (TAFB), a more efficient and adaptive fusion of weights for denoising.
- 12
- 12
- 11
- 11
- 11
- 10
- Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations10
A dynamic filter network integrating global and local branches to address prevalent degradation modalities, which outperforms state-of-the-art blind super-resolution algorithms in both synthetic and real image datasets.
- 10
- 10
- 9
- 9
- 9
- 9
- FaceInsight: A Multimodal Large Language Model for Face Perception8
FaceInsight is proposed, a versatile face perception MLLM that provides fine-grained information and introduces visual textual alignment of facial knowledge to model both uncertain dependencies and deterministic relationships among facial information, mitigating the limitations of language-driven reasoning.
- 8
- Multi-scale, multi-dimensional binocular endoscopic image depth estimation network8
An end-to-end multi-scale supervisory depth estimation network (MMDENet) model for the depth estimation of pairs of binocular images, with a processing time of approximately 30fps, satisfying the requirements of real-time operation applications.
- Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection7
A novel disentangled representation learning framework for deepfake detection that extends reconstruction loss from image-level to feature-level, and proposes a critical forgetting mechanism that forces the detector to forget the most salient features during training, which correspond to specific forgery artifact types in the training set.
- LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt Tuning7
A novel robust UAV tracker termed LVPTrack is proposed, which conducts high quality label-aligned visual prompt tuning to adapt to various challenging weather conditions and achieves superior performance over existing state-of-the-art UAV trackers.
- 7
- SIGMA-DF: Single-Side Guided Meta-Learning for Deepfake Detection7
A novel method named Single-sIde Guided Meta-leArning framework for DeepFake detection (SIGMA-DF) which simulates the cross-domain scenarios during training by synthesizing virtual testing domain through meta-learning, which achieves state-of-the-art performance on unseen Deepfake data.
- 7
- Nighttime Image Dehazing Based on Multi-Scale Gated Fusion Network7
An efficient algorithm to directly restore a clear image from a hazy input, which can be adapted for nighttime image dehazing, which hinges on a trainable neural network realized in an encoder–decoder architecture.
- UMDATrack: Unified Multi-Domain Adaptive Tracking under Adverse Weather Conditions6
This paper proposes UMDATrack, which is capable of maintaining high-quality target state prediction under various adverse weather conditions within a unified domain adaptation framework and proposes a target-aware confidence alignment module (TCA) following optimal transport theorem.
- Insert or Attach: Taxonomy Completion via Box Embedding6
The framework, TaxBox, leverages box containment and center closeness to design two specialized geometric scorers within the box embedding space, tailored for insertion and attachment operations and can effectively capture intrinsic relationships between concepts by optimizing on a granular box constraint loss.
- MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration6
This paper focuses on the task of low-light image enhancement (LLIE) and proposes a novel LLIE method called MixNet, which is designed explicitly for UHD images and surpasses the performance of current state-of-the-art methods.
- Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors6
Hero-SR is a one-step diffusion-based SR framework explicitly designed with human perception priors, which generates high-resolution images that not only preserve intricate details but also reflect human perceptual preferences.
- 6
- 5
- 5
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution5
This paper proposes an unsupervised diffusion-based degradation modeling framework (UDDM) to effectively capture real-world degradation distributions and introduces a physics-based dynamic degradation module (P-DDM) that adaptively models content-aware degradation, ensuring both content and structural accuracy.
- 5
- 4
- Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection4
A novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection and shows promise for practical large-scale power line inspections with unmanned aerial vehicles.
- 4
- 4
- 4
- 4
- CDIR: LoRA-Inspired Attention for Efficient Composite Degradation Image Restoration3
The proposed network, CDIR, achieves state-of-the-art performance with significantly reduced complexity and fast inference speed, and shows strong adaptability to various task-specific image restoration scenarios, such as dehazing, desnowing, and deraining.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion2
A novel framework that improves the separation of identity-related and identity-unrelated features and introduces an innovative feature fusion mechanism to improve the quality and text alignment of generated images is proposed.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- Efficient All-in-One Image Restoration With Adaptive Frequency Enhancement1
This paper proposes AdaptIR, an efficient all-in-one image restoration network equipped with adaptive frequency enhancement, which achieves state-of-the-art performance on all-in-one image restoration tasks involving multiple degradations, while maintaining high computational efficiency.
- 1
- Detecting Synthetic Image by Cross-Modal Commonality Interaction1
This work proposes a multi-modal high-frequency interactive detection framework for general synthetic image detection that explicitly integrates high-frequency information from both the spatial and frequency domains and achieves state-of-the-art performance in real-world detection scenarios.
- 1
- 1
- Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models1
- How Powerful Potential of Attention on Image Restoration?1
This paper proposes Continuous Scaling Attention (CSAttn), a method that computes attention continuously in three stages without using FFN and applies it to several image restoration tasks and shows that it can outperform CNN-based and Transformer-based image restoration approaches.
- An unsupervised medical image registration network for intelligent medical education1
A cross-view interactive network (CVIN) is proposed, which utilizes alternate stages with information interaction modules to extract data features, which can use unlabeled medical data to train the model and introduces an InfoMax module to learn the mutual information between registered images.
- 1
- Unpaired Overwater Image Defogging Using Prior Map Guided CycleGAN1
An intuitive Upscaling Inception Module (UIM) and a Long-range Residual Coarse-to-fine framework (LRC) to mitigate the issue of under-constrained domain mapping from foggy to fog-free image, leading to artifacts and loss of details.
- Single Image Dehazing Using Sparse Contextual Representation1
In this paper, a novel method to remove haze from a single hazy input image based on the sparse representation is proposed to be used as a contextual regularization tool, which can reduce the block artifacts and halos produced by only using dark channel prior without soft matting.
- Benchmarking Deep Deblurring Algorithms: A Large-Scale Multi-Cause Dataset and A New Baseline Model.1
- 1
- –
- –
- –
- Large Kernel Network for Efficient Image Restoration–
This paper proposes a simple and efficient large kernel network for image restoration, termed ArtIR, motivated by the channel redundancy observed in image restoration models, and applies adaptive large-kernel operations to a collapsed single channel and employs an ultra-lightweight channel attention mechanism to restore channel diversity.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- DyLoRA-TAD: Dynamic Low-Rank Adapter for End-to-End Temporal Action Detection–
Dynamic Low-Rank Adapter (DyLoRA), a lightweight fine-tuning framework tailored specifically for the TAD task, enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights, thereby alleviating the representation misalignment of temporal features.
- 4KDehazeFlow: Ultra-High-Definition Image Dehazing via Flow Matching–
This method models the dehazing process as a progressive optimization of continuous vector field flow, providing efficient data-driven adaptive nonlinear color transformation for high-quality dehazing.
- –
- –
- –
- –
- –
- –
- Image Dehazing: Improved Techniques–
Two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset are explored: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding of hazy images.
- CONVEF-based Fourth-order Anisotropic Diffusion for Image Denoising–
The convolutional virtual electric field (CONVEF) into the fourth-order PDE for images restoration is introduced since the CONVEF based fourth- order model possesses anisotropic properties over the image features, which leads to improvement on noise removal and edge and texture preserving over the original model.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.