Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks188 from public data
- Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement2,430
A novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network and shows that it generalizes well to diverse lighting conditions.
- 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).
- Underwater scene prior inspired deep underwater image and video enhancement1,262
An underwater image enhancement convolutional neural network model based on underwater scene prior based on underwater scene prior is proposed, called UWCNN, which directly reconstructs the clear latent underwater image, which benefits from the underwater scene prior which can be used to synthesize underwater image training data.
- 936
- Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation915
A novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network and demonstrates the advantages of the method over state-of-the-art methods qualitatively and quantitatively.
- 891
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey651
This paper proposes a low-light image and video dataset, in which the images and videos are taken by different mobile phones’ cameras under diverse illumination conditions, and provides a unified online platform that covers many popular LLIE methods.
- 600
- 532
- LightenNet: A Convolutional Neural Network for weakly illuminated image enhancement515
A trainable Convolutional Neural Network is proposed for weakly illuminated image enhancement, namely LightenNet, which takes a weakly illumination image as input and outputs its illumination map that is subsequently used to obtain the enhanced image based on Retinex model.
- 439
- Towards Robust Blind Face Restoration with Codebook Lookup Transformer434
This paper demonstrates that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces.
- 407
- Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images355
An end-to-end Dense Attention Fluid Network (DAFNet) for SOD in optical RSIs that significantly outperforms the existing state-of-the-art SOD competitors is proposed and a new and challenging optical RSI dataset is constructed that contains 2,000 images with pixel-wise saliency annotations.
- PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators351
This paper proposes a physical model-guided GAN model for UIE, referred to as PUGAN, and designs the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results.
- 345
- Diving deeper into underwater image enhancement: A survey315
The underwater image formation models are introduced, which are the base of training data synthesis and design of deep networks, and also helpful for understanding the process of underwater image degradation and the robustness and effectiveness of deep algorithms.
- ProPainter: Improving Propagation and Transformer for Video Inpainting267
This work introduces dual-domain propagation that combines the advantages of image and feature warping, exploiting global correspondences reliably, and proposes a mask-guided sparse video Transformer, which achieves high efficiency by discarding unnecessary and redundant tokens.
- 267
- LEDNet: Joint Low-Light Enhancement and Deblurring in the Dark258
This work introduces a novel data synthesis pipeline that models realistic low-light blurring degradations and presents the first large-scale dataset, LOL-Blur, and an effective network, named LEDNet, to perform joint low-light enhancement and deblurring.
- 251
- RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors241
This work rethink the degradation of real hazy images and proposes a phenomenological pipeline considering diverse degradation types, which drastically mitigates the domain gap between synthetic and real data, and recalculates the distance when matching the features to the HQPs by a controllable matching operation, which facilitates finding better counterparts.
- 240
- 238
- CIR-Net: Cross-Modality Interaction and Refinement for RGB-D Salient Object Detection231
A convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement is presented, which outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively.
- Iterative Prompt Learning for Unsupervised Backlit Image Enhancement230
A novel unsupervised backlit image enhancement method by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel-level image enhancement, which outperforms state-of-the-art methods in terms of visual quality and generalization ability.
- A hybrid method for underwater image correction223
Subjective and objective performance evaluations demonstrate that the proposed method significantly improves both color and visibility of degraded underwater images, and is comparable to and even outperforms several state-of-the-art methods.
- Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement222
This work proposes a new solution, UHDFour, that embeds Fourier transform into a cascaded network and contributes the first real UHD LLIE dataset, \textbf{UHD-LL}, that contains 2,150 low-noise/normal-clear 4K image pairs with diverse darkness and noise levels captured in different scenarios.
- Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement218
A novel semantic-aware knowledge-guided framework that can assist a low-light enhancement model in learning rich and diverse priors encapsulated in a semantic segmentation model and is appealing in acting as a general framework in LLIE task.
- HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement210
The HCLR-Net, a novel approach built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability.
- 207
- 206
- 205
- An In-Depth Survey of Underwater Image Enhancement and Restoration197
This exposition summarizes more than 120 studies about the latest progress in underwater image restoration and enhancement, including the techniques, datasets, available codes, and evaluation metrics, and provides detailed objective evaluations and analysis of the representative methods on five types of underwater scenarios, which verifies the applicability of these methods in different underwater conditions.
- 187
- 179
- 175
- RGB-D Salient Object Detection with Cross-Modality Modulation and Selection149
A cross-modality feature modulation module to enhance feature representations by taking the depth features as prior, which models the complementary relations of RGB-D data and an adaptive feature selection module to select saliency-related features and suppress the inferior ones.
- CVANet: Cascaded visual attention network for single image super-resolution148
This work presents a Cascaded Visual Attention Network for SISR called CVANet, which simulates the visual attention mechanism of the human eyes to focus on the reconstruction process of details and outperforms the state-of-the-art (SOTA) methods in subjective visual perception, PSNR, and SSIM.
- 123
- Image colorization: A survey and dataset115
This article presents a comprehensive survey of recent state-of-the-art colorization using deep learning algorithms, describing their fundamental block architectures in terms of skip connections, input etc as well as optimizers, loss functions, training protocols, and training data etc.
- 115
- Flare7K: A Phenomenological Nighttime Flare Removal Dataset114
Flare7K is introduced, the first nighttime flare removal dataset, which is generated based on the observation and statistics of real-world nighttime lens flares, and offers 5,000 scattering and 2,000 reflective flare images, consisting of 25 types of scattering flares and 10 types of reflective flares.
- 113
- A parallel down-up fusion network for salient object detection in optical remote sensing images108
A novel Parallel Down-up Fusion network (PDF-Net) for SOD in optical RSIs, which takes full advantage of the in-path low- and high-level features and cross-path multi-resolution features to distinguish diversely scaled salient objects and suppress the cluttered backgrounds.
- Global-and-Local Collaborative Learning for Co-Salient Object Detection105
The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that the model trained on a small dataset still outperforms 11 state-of-the-art competitors trained on some large datasets.
- A Cascaded Convolutional Neural Network for Single Image Dehazing105
Qualitatively and quantitatively experimental results demonstrate that the proposed method effectively removes haze from such images, and outperforms several state-of-the-art dehazing methods.
- 99
- Underwater image enhancement by dehazing and color correction96
The enhanced images, as a result of implementing the proposed approach, are characterized by relatively genuine color, increased contrast and brightness, reduced noise level, and better visibility.
- 93
- Empowering Low-Light Image Enhancer through Customized Learnable Priors90
A paradigm for low-light image enhancement that explores the potential of customized learnable priors to improve the transparency of the deep unfolding paradigm is proposed and extensive experiments demonstrate the superiority of the proposed paradigm over state-of-the-art methods.
- 88
- Examining imbalanced classification algorithms in predicting real-time traffic crash risk84
The proposed method of improving prediction accuracy in this study is universal and can be applied to many other prediction models to predict real-time traffic crash risk.
- 83
- Deep Fourier Up-Sampling80
The relationships between spatial and Fourier domains are revisited and the transform rules on the features of different resolutions in the Fourier domain are revealed, which provide key insights for FourierUp's designs.
- 80
- Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond79
Flare7K++ is introduced, the first comprehensive nighttime flare removal dataset, consisting of 962 real-captured flare images (Flare-R) and 7000 synthetic flares (Flare7K), and a new end-to-end pipeline to preserve the light source while removing lens flares.
- GIFM: An Image Restoration Method With Generalized Image Formation Model for Poor Visible Conditions75
- 70
- Underwater Optical Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future68
This survey comprehensively study AI-based UOD by categorising existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarising them by considering learning strategies, experimental datasets, learning stages, employed features or techniques, and underlying frameworks.
- DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution68
This work proposes the DiT4SR, one of the pioneering works to tame the large-scale DiT model for Real-ISR, which endow the DiT model with superior performance in Real-ISR, which is demonstrated by extensive experiments.
- LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation67
This study designs a first-frame-conditioned pipeline that uses an off-the-shelf text-to-image model for content generation so that the authors' tuned video diffusion model mainly focuses on motion learning, and develops an effective inference trick, shared-noise sampling, which can improve the stability of videos with computational costs.
- Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network65
A physics-based image formation model is defined to better understand the degradation of Under-Display Camera images, and a new domain knowledge-enabled Dynamic Skip Connection Network (DISCNet) is designed to restore the UDC images.
- 61
- 59
- 58
- Adaptively Learning Low-high Frequency Information Integration for Pan-sharpening55
A novel pan-sharpening framework by adaptively learning low-high frequency information integration in the spatial and frequency dual domains by adaptingively learning the modality-aware frequency information difference of PAN and MS images and further predicting the low- high frequency boundary in the form of a two-dimensional mask.
- Multiscale transunet + + : dense hybrid U-Net with transformer for medical image segmentation54
A weighted loss function composed of focal, multiscale structure similarity and Jaccard index is employed to penalize the training error of medical image segmentation, jointly realizing pixel-level, patch-level and map-level optimization.
- Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing53
A novel Iterative Predictor-Critic Code Decoding framework for real-world image dehazing, abbreviated as IPC-Dehaze, which leverages the high-quality codebook prior encapsulated in a pre-trained VQGAN to improve code prediction accuracy and ensure stable dehazing performance.
- Underwater image restoration via feature priors to estimate background light and optimized transmission map52
This work develops a robust model to estimate the background light according to feature priors of flatness, hue, and brightness, which can effectively relieve color distortion and compensate the red channel of color corrected image to revise the transmission map of it.
- Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior50
This work proposes an optical center symmetry prior, which suggests that the reflective flare and light source are always symmetrical around the lens's optical center, and creates the first reflective flare removal dataset called BracketFlare, which contains diverse and realistic reflective flare patterns.
- Single underwater image enhancement based on color cast removal and visibility restoration50
Experimental results demonstrate that the proposed underwater image-enhancement method can effectively remove color cast, improve contrast and visibility, and recover natural appearance of degraded underwater images.
- Conditional mutual information-based feature selection algorithm for maximal relevance minimal redundancy48
A feature selection algorithm based on conditional mutual information for maximal relevance minimal redundancy (CMI-MRMR) is proposed and compared with several feature selection algorithms to validate the performance and show that it can achieve better feature selection performance.
- EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation46
Two new methods to evaluate the image-text alignment capabilities of T2I models are introduced: FGA-BLIP2 which involves end-to-end fine-tuning of a vision-language model to produce fine-grained image-text alignment scores and PN-VQA which adopts a novel positive-negative VQA manner in VQA models for zero-shot fine-grained evaluation.
- 45
- 44
- Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery44
This paper proposes a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
- 42
- 42
- 41
- Investigating Attention Mechanism in 3D Point Cloud Object Detection41
This work investigates the role of the attention mechanism in 3D point cloud object detection and provides insights into the potential of different attention modules, including the latest point cloud transformers on SUN RGB-D and ScanNetV2 datasets.
- Fast color balance and multi-path fusion for sandstorm image enhancement39
A fast color balance method followed by an effective fusion model is proposed to enhance the sandstorm-degraded images and outperforms existing enhancement algorithms of sandstorm image via qualitative and quantitative evaluations.
- 37
- 35
- 33
- TIENet: task-oriented image enhancement network for degraded object detection32
A task-oriented image enhancement network (TIENet) to directly improve degraded object detection’s performance by enhancing the degraded images by presenting a fast Fourier transform-based structure loss for the enhancement task.
- NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results30
A comprehensive overview of the NTIRE 2025 Efficient Burst HDR and Restoration Challenge is provided, the proposed solutions are compared, and it serves as a valuable reference for researchers and practitioners in efficient burst HDR and restoration.
- Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration30
This paper proposes a simple pipeline for all-in-one blind image restoration to Restore Anything with Masks (RAM), and focuses on the image content by utilizing Mask Image Modeling to extract intrinsic image information rather than distinguishing degradation types like other methods.
- Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera30
This work revisits the classic stereo setup for training data collection and mitigate the non-trivial domain discrepancy and spatial misalignment through a novel Transformer-based framework that generates well-aligned yet high-quality target data for the corresponding UDC input.
- 29
- The Orientation Estimation of Elongated Underground Objects via Multipolarization Aggregation and Selection Neural Network28
This letter proposes a multipolarization aggregation and selection network (MASNet), which takes the multipolarimetric radargrams as inputs, integrates their characteristics in the feature space, and selects discriminative features of reflected signal patterns for accurate orientation estimation.
- Estimating Parameters of the Tree Root in Heterogeneous Soil Environments via Mask-Guided Multi-Polarimetric Integration Neural Network27
A novel neural network architecture, called mask-guided multi-polarimetric integration neural network (MMI-Net), is proposed to automatically and simultaneously estimate multiple root-related parameters in heterogeneous soil environments and achieves high estimation accuracy.
- Learning Inclusion Matching for Animation Paint Bucket Colorization26
This work introduces a new learning-based inclusion matching pipeline, which directs the network to comprehend the inclusion relationships between segments rather than relying solely on direct visual correspondences, enabling more nuanced and accurate colorization.
- 26
- 26
- Normalization-based Feature Selection and Restitution for Pan-sharpening26
A Normalization-based Feature Selection and Restitution mechanism, which is capable of filtering out the inconsistent features and promoting to learn the consistent ones, thus relieving the over-transferred artifacts in the process of PAN-guided MS super-resolution.
- Improve Aggressive Driver Recognition Using Collision Surrogate Measurement and Imbalanced Class Boosting26
CUSBoost achieves the highest or the second-highest Area Under Precision-Recall Curve (AUPRC) in most datasets and is found the discrete Fourier coefficients of gap as the key feature to identify aggressive drivers.
- 25
- 25
- 25
- Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future24
This survey comprehensively study AI-based UOD, categorising existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarising them by considering learning strategy, experimental dataset, utilised features or frameworks, and learning stage.
- CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustment23
This work presents Curve Distillation, CuDi, for efficient and controllable exposure adjustment without the requirement of paired or unpaired data during training, which corrects both underexposed and overexposed photos with a single model.
- 23
- BeautyREC: Robust, Efficient, and Component-Specific Makeup Transfer23
The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeupTransfer, and enabling efficient makeup transfer via a single-path structure.
- Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network22
This paper formulate pan-sharpening as an alternately iterative reverse filtering process, which fuses LR MS and HR MS in an interpretable manner, and develops the learnable multi-scale Gaussian kernel module, instead of using specific filters.
- 22
- A feature selection algorithm based on redundancy analysis and interaction weight22
A feature selection algorithm based on redundancy analysis and interaction weight is proposed in this paper, which can obtain better feature selection performance.
- NuI-Go: Recursive Non-Local Encoder-Decoder Network for Retinal Image Non-Uniform Illumination Removal22
A non-uniform illumination removal network for retinal image, called NuI-Go, which consists of three Recursive Non-local Encoder-Decoder Residual Blocks (NEDRBs) for enhancing the degraded retinal images in a progressive manner is proposed.
- A Feature Selection Algorithm Based on Equal Interval Division and Minimal-Redundancy–Maximal-Relevance22
Experimental results demonstrate that the EID–mRMR algorithm can achieve better feature selection performance, and the idea of equal interval division is proposed and combined with ranking to process the interval of mutual information between features and the class label.
- 21
- Learning to remove sandstorm for image enhancement21
A method equipped with color correction and an unsupervised learning network is proposed to enhance sandstorm images and demonstrates that it outperforms several state-of-the-arts both qualitatively and quantitatively.
- Crash Injury Severity Prediction Using an Ordinal Classification Machine Learning Approach21
Converting severity levels into three classes, minor injury, moderate injury, and serious injury, can substantially improve the prediction precision and is proved to be superior to other ordinal classification methods and nominal classification machine learning by statistical significance test.
- 18
- 18
- MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results18
The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal and a detailed description of all models developed is provided in this paper.
- Submersion simulation in a typical debris flow watershed of Jianzhuangchuan catchment, Loess Plateau17
- An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data16
The results show that the OneClassSVM detection algorithm can be effectively applied to the identification of dangerous driving behavior, and the improved Xgboost algorithm performs best for the extremely imbalanced data of dangerous drivers.
- MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results15
The developed solutions in this challenge achieved state-of-the-art performance on Few-shot RAW Image Denoising and were summarized and reviewed in this paper.
- JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancement15
This study proposes JoReS-Diff, a novel approach that incorporates Retinex- and semantic-based priors as the additional pre-processing condition to regulate the generating capabilities of the diffusion model.
- DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models14
Direct Discrepancy Learning (DDL) is proposed, a novel optimization strategy that directly optimizes the detector with task-oriented knowledge and enables the detector to better capture the core semantics of the detection task, thereby enhancing both robustness and generalization.
- 14
- 14
- Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-Spectral Image Fusion13
A novel model-driven deep unfolding framework with image reasoning prior tailored for the pan-sharpening task, motivated by the content reasoning ability of masked autoencoders (MAE) with insightful designs that penetrate the image reasoning prior into deep unfolding networks while improving its interpretability and representation capability.
- 12
- Adaptive Window Pruning for Efficient Local Motion Deblurring12
This paper proposes a local motion deblurring vision Transformer built on adaptive window pruning Transformer blocks (AdaWPT), and removes local motion blur effectively without distorting sharp regions, demonstrated by its exceptional perceptual and quantitative improvements compared to state-of-the-art methods.
- Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark12
Photos captured in such a condition significantly impact the performance of various nighttime activities, such as autonomous driving, surveillance systems, and so on.
- A Feature Selection Algorithm Based on Equal Interval Division and Conditional Mutual Information12
This paper proposes an objective function based on conditional mutual information, a method of equal interval division and ranking with the objective function to select features, and proposes a feature selection algorithm named EID-CMI that can achieve better feature selection performance.
- Nighttime image dehazing using color cast removal and dual path multi-scale fusion strategy12
The visual effect of the hazy nighttime images in real-world datasets can be significantly improved by the method regarding contrast, color fidelity, and visibility and outperforms the state-of-the-art methods qualitatively and quantitatively.
- Generalizing ISP Model by Unsupervised Raw-to-raw Mapping11
The proposed unsupervised raw-to-raw model achieved performance comparable to that of the state-of-the-art semi-supervised method in raw-to-raw task, and its ability to generalize the ISP model across different cameras was assessed.
- 11
- 11
- 10
- 10
- 10
- 9
- 9
- Blind face images deblurring with enhancement9
A generative adversarial network (GAN) is proposed, which includes a perception-inspired blurry removal generator and a discriminator that reconstructs the latent deblurred image by a U-net based network that contains an enhancement module.
- 9
- MIPI 2023 Challenge on RGBW Remosaic: Methods and Results8
This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023, and describes the top three models developed in this challenge.
- 7
- 7
- Underwater image enhancement by maximum-likelihood based adaptive color correction and robust scattering removal7
An adaptive color correction algorithm based on the maximum likelihood estimation of Gaussian parameters, which effectively removes color casts of a variety of underwater images and achieves competitive performance with the state-of-the-art methods in terms of objective evaluation metrics, which validates the better robustness and higher generalization ability of the enhancement model.
- MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Results6
The results of the competition are presented, the strengths and weaknesses of the top-performing methods are analyzed, and the implications of the findings for future research in RGB+sparse ToF depth completion are discussed.
- Image compressed sensing based on non-convex low-rank approximation6
The experimental results show that the proposed non-convex low-rank regularization namely weighted Schatten p-norm minimization (WSNM) outperforms the state-of-the-art CS recovery algorithms not only in PSNR index, but also in local structure preservation.
- Hierarchical feature concatenation-based kernel sparse representations for image categorization6
This paper proposes to find sparse representation based on feature concatenation using hierarchical kernel orthogonal matching pursuit (HKOMP) and shows that the proposed scheme outperforms many kernel learning based and other competitive image categorization algorithms.
- 6
- 5
- 5
- Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset4
The first underwater camouflaged instance segmentation (UCIS) dataset is introduced, abbreviated as UCIS4K, which comprises 3,953 images of camouflaged marine organisms with instance-level annotations and an Underwater Camouflaged Instance Segmentation network based on Segment Anything Model (UCIS-SAM).
- 4
- MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results4
The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal and the developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal.
- 4
- 4
- BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer4
In what follows, this work details the network structure and parameters, including contentEncoder, style encoder, componentspecific correspondence, long-range dependencies, and image reconstruction, including how the component-specific transferred features and the global transferred features are concatenated with the corresponding decoder features.
- 4
- 3
- Semantic segmentation in adverse scenes with fewer labeled images3
This study proposes a novel two-step training pipeline that separately handles the training of labeled and unlabeled images to prevent overfitting, and develops a class adaptive threshold with label perception (CATLP) to generate accurate pseudo-labels.
- 3
- 3
- MIPI 2023 Challenge on RGBW Fusion: Methods and Results3
This paper summarizes and reviews the RGBW Joint Fusion and Denoise track on MIPI 2023 and describes the models developed in this challenge, including PSNR, SSIM, LPIPS, and KLD.
- A visual hierarchical framework based model for underwater image enhancement3
A visual hierarchical framework based model inspired by retinal mechanism, which restores the distortion from color cast and increases contrast simultaneously for underwater images by simulating visual processing of the mammalian retina is proposed.
- Manmade target extraction based on multistage decision and its application for change detection in polarimetric synthetic aperture radar image3
A universal framework of change detection for manmade targets is presented as an application of the proposed multistage decision-based method based on the theories of polarimetric contrast enhancement, generalized Y decomposition, and maximum eigenvalue ratio.
- 3
- 2
- 2
- ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images2
This study establishes the first large-scale Visual Distortion Assessment Instruction Tuning Dataset for UGC images, termed ViDA-UGC, which comprises 11K images with fine-grained quality grounding, detailed quality perception, and reasoning quality description data.
- Advances of low-level vision reconstruction in raw domain2
This review focuses on the low - level vision reconstruction technology in the raw domain and mainly investigates the progress of deep learning - based vision reconstruction.
- 2
- Unlocking Masked Autoencoders as Loss Function for Image and Video Restoration2
This work stands on the shoulders of the masked Autoencoders (MAE) and formulate it as a `learned loss function', owing to the fact the pre-trained MAE innately inherits the prior of image reasoning.
- A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution1
A new dataset, 360Insta, is introduced that comprises authentically degraded omnidirectional images and videos collected under diverse conditions, including varying lighting, motion, and exposure settings, that addresses a critical gap in current omnidirectional benchmarks and enables more robust evaluation of the generalization capabilities of omnidirectional super-resolution methods.
- Tree-Mamba: A Tree-Aware Mamba for Underwater Monocular Depth Estimation1
A novel tree-aware Mamba method that adaptively constructs a minimum spanning tree based on feature similarity that demonstrates the superiority of the proposed Tree-Mamba over several leading methods in both qualitative results and quantitative evaluations with competitive computational efficiency.
- Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring1
A Frequency-Driven Inverse Kernel Prediction network (FDIKP) that incorporates frequency-domain representations to enhance structural identifiability in kernel modeling and outperforms existing approaches in single image defocus deblurring.
- Random Weights Networks Work as Loss Prior Constraint for Image Restoration1
The main focus is to spark the realms of loss function and save their current neglected status and present the belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''.
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; 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.