Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks83 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).
- 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.
- 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
- 373
- 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.
- 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.
- Towards An End-to-End Framework for Flow-Guided Video Inpainting234
An End-to-End framework for Flow-Guided Video Inpainting (E2 FGVI) through elaborately designed three trainable modules, namely, flow completion, feature propagation, and content hallucination modules that can be Jointly optimized, leading to a more efficient and effective inpainting process.
- AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation229
This work presents All-Pairs Multi-Field Transforms (AMT), a new network architecture for video frame interpolation based on two essential designs that derive multiple groups of fine-grained flow fields from one pair of updated coarse flows for performing backward warping on the input frames separately.
- 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.
- 207
- 205
- 175
- 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.
- 100
- The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report91
This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes, and gauge the state-of-the-art in efficient single-image super-resolution.
- 88
- 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.
- 68
- 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.
- 61
- 58
- 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.
- 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.
- 44
- 42
- Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory41
This work introduces a Hierarchical Pose-free Memory Compressor that recursively distills historical latents into a fixed-budget representation, and proposes an Uncertainty-aware Action Labeling module that discretizes continuous motion into a tri-state logic.
- SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution39
This paper presents SRFormer, a simple but novel method that can enjoy the benefit of large window self-attention but introduces even less computational burden, and attempts to scale up the model by further enlarging the window size and channel numbers to explore the potential of Transformer-based models.
- 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.
- 26
- 25
- 25
- 25
- 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.
- 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.
- NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)21
An overview of the NTIRE 2026 challenge is presented, establishing a novel benchmark exploring the ability of MLLMs to mimic human expert cognition in evaluating high-quality image pairs, and identifying the visually superior image within a high-quality pair.
- 21
- Towards RAW Object Detection in Diverse Conditions18
This work introduces the AODRaw dataset, which offers 7,785 high-resolution real RAW images with 135,601 annotated instances spanning 62 categories, capturing a broad range of indoor and outdoor scenes under 9 distinct light and weather conditions, and provides a comprehensive benchmark for evaluating current detection methods.
- 18
- InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration15
Treating low-quality images as the intermediate state of LCM, InterLCM achieves a balance between fidelity and quality by starting from earlier LCM steps and incorporates a Visual Module to extract visual features and a Spatial Encoder to capture spatial details, enhancing the fidelity of restored images.
- 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.
- Image Harmonization by Matching Regional References15
This work firstly match the contents between the foreground and background and then adaptively adjust every foreground location according to the appearance of its content-related background regions, and design a residual reconstruction strategy that uses the predicted residual to adjust the appearance.
- 15
- 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.
- 3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics-Based Appearance–Medium Decoupling11
A physics-based framework that disentangles object appearance from water medium effects through tailored Gaussian modeling is proposed and a depth-guided optimization strategy that leverages pseudo-depth maps as supervision with depth regularization and scale penalty terms to improve geometric fidelity is proposed.
- 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.
- EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation9
An efficient automated evaluation method termed FGA-BLIP2 is introduced, which enables Fine-Grained Alignment evaluation solely by inputting images and text leveraging BLIP2, without visual question answering for each fine-grained element.
- 9
- Unpaired remote sensing image super-resolution with content-preserving weak supervision neural network9
This paper presents a meta-modelling framework that automates the very labor-intensive and therefore time-heavy and expensive and therefore expensive and expensive process of computer programming called “supercomputing”.
- 9
- A Diffusion-Based Framework for Occluded Object Movement7
This work proposes a Diffusion-based framework specifically designed for Occluded Object Movement, named DiffOOM, which consists of two parallel branches that perform object de-occlusion and movement simultaneously.
- Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable6
This work proposes a differentiable denoising pipeline based on traditional methods that involves a neural network being trained to predict the optimal denoising parameters for each specific input, resulting in a robust and efficient approach that also supports user control.
- 5
- 5
- 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.
- 3
- DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts3
This paper proposes a diffusion-based method, named DiffRetouch, which can capture the complex fine-retouched distribution covering various visual-pleasing styles in the training data and makes four image attributes adjustable to provide a user-friendly editing mechanism.
- 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
- KnifeCut: Refining Thin Part Segmentation with Cutting Lines3
This work proposes KnifeCut, which is the first method to solve interactive thin structure refinement pertinently and offers the users two results, where one only focuses on the target thin part and the other provides the refinements for all thin parts that share similar features with the target one.
- 2
- 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.
- 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.
- 1
- 1
- 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.
- 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''.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- MB-DAMPNet: a novel multi-branch denoising-based approximate message passing algorithm via deep neural network for image reconstruction–
A novel multi-branch denoising-based approximate message passing algorithm via deep neural network, dubbed MB-DAMPNet, which significantly outperforms other state-of-the-art methods in image reconstruction accuracy.
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.