Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks172 from public data
- Multi-Scale Progressive Fusion Network for Single Image Deraining859
This work explores the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi- scale progressive fusion network (MSPFN) for single image rain streak removal.
- 544
- 473
- 410
- 332
- EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution281
Different from previous works using heavy UNet for noise prediction, an efficient activation network (EANet) is developed to achieve favorable noise prediction performance by simplified channel attention and simple gate operation, which dramatically reduces the computational budget.
- Hierarchical dense recursive network for image super-resolution242
A novel hierarchical dense connection network (HDN) is advocated for image SR that outperforms the state-of-the-art methods in terms of quantitative indicators and realistic visual effects, as well as enjoys a fast and accurate reconstruction.
- 228
- Unpaired Deep Image Deraining Using Dual Contrastive Learning205
An effective unpaired SID adversarial framework which explores mutual properties of the unpaired exemplars by a dual contrastive learning manner in a deep feature space, named as DCD-GAN is developed.
- 190
- Local-Global Temporal Difference Learning for Satellite Video Super-Resolution180
A Short-term Temporal Difference Module is devised to extract local motion representations from RGB difference maps between adjacent frames, which yields more clues for accurate texture representation and a Difference Compensation Unit (DCU) is proposed to enrich the interaction between the spatial distribution of the target frame and temporal compensated results.
- 173
- Deep Distillation Recursive Network for Remote Sensing Imagery Super-Resolution144
Experiments on Kaggle Open Source Dataset and Jilin-1 video satellite images illustrate that DDRN outperforms the conventional CNN-based baselines and some state-of-the-art feature extraction approaches.
- 131
- 129
- 115
- A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends107
This survey provides the first in-depth and systematic overview of AiOIR, delivering a structured taxonomy that categorizes existing methods by architectural designs, learning paradigms, and their core innovations, and systematically categorizes current approaches and assess the challenges these models encounter.
- 107
- Magic ELF: Image Deraining Meets Association Learning and Transformer102
This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining, and introduces degradation prior to help background recovery and presents the association refinement deraining scheme.
- 96
- Ultra-dense GAN for satellite imagery super-resolution89
An ultra-dense GAN (udGAN) is proposed for image SR, where the internal layout of the residual block is reformed into a two-dimensional matrix topology, which can provide additional diagonal connections so that the model can still accomplish enough pathways with fewer layers.
- 85
- 72
- Degrade Is Upgrade: Learning Degradation for Low-Light Image Enhancement68
A novel two-step generation network for degradation learning and content refinement, which is not only superior to one-step methods, but also capable of synthesizing sufficient paired samples to benefit the model training.
- 64
- DAWN: Direction-aware Attention Wavelet Network for Image Deraining61
A novel Direction-aware Attention Wavelet Network (DAWN) for rain streaks removal that delivers significant performance gains on nine datasets across image deraining and object detection tasks, exceeding the state-of-the-art method MPRNet by 0.88 dB in PSNR on the Test1200 dataset.
- 60
- 54
- Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution52
A simple yet effective fully 1 × 1 convolutional network, named shift-Conv-based network (SCNet), equipped with a powerful representation capability and impressive computational efficiency, which can be exploited for lightweight SISR tasks.
- Rainy WCity: A Real Rainfall Dataset with Diverse Conditions for Semantic Driving Scene Understanding50
A real, comprehensive, and well-annotated scene understanding dataset under rainy weather, named Rainy WCity is pioneer, which covers various rain patterns and their bring-in negative visual effects and an unsupervised contrastive learning network for real image deraining and the final rainy scene semantic segmentation via multi-task joint optimization is designed.
- 47
- Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning46
A one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR is proposed, which makes full use of spatial-temporal correlations via the mutual learning between S-V SR and T-vSR, to exploit the mutual information among them via iterative up-and-down projections.
- 45
- When Face Recognition Meets Occlusion: A New Benchmark44
A simulated occlusion face recognition dataset that combines original normal face images and occluded face images to form the final dataset, termed as Webface-OCC, which significantly outperforms the state-of-the-arts face recognition models trained on existing datasets.
- 41
- PLFace: Progressive Learning for Face Recognition with Mask Bias41
Compared to state-of-the-art competitors, the proposed PLFace significantly improves the accuracy of MFR while maintaining the performance of normal face recognition.
- 40
- Image-free single-pixel keypoint detection for privacy preserving human pose estimation36
An image-free human keypoint detection technique using a few coded illuminations and a single-pixel detector that can complete the keypoint detection task at an ultralow sampling rate on a measured one-dimensional sequence without image reconstruction, thus protecting privacy from the data collection stage and preventing the acquisition of detailed visual information from the source.
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- 33
- 33
- 32
- 30
- 29
- 29
- 28
- DANet: Image Deraining via Dynamic Association Learning28
This work proposes a dynamic associated network (DANet) to achieve the association learning between rain streak removal and background recovery, and introduces the parametric association constraint for enhancing the compatibility of deraining model with background reconstruction.
- 27
- Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting27
This paper provides a complete overview of current VI-ReID approaches that employ deep learning algorithms, and compares ReID with VI- re-identification in three aspects, including data composition, challenges, and performance.
- 26
- 26
- 26
- 26
- 26
- Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification25
The dynamic instance sampling and reinforcement learning are integrated into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more cred-ible decision-making.
- 25
- 24
- 24
- You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution21
An effective yet efficient recurrent network with bidirectional interaction for ST-VSR, where only one alignment and fusion is needed, and a Hybrid Fusion Module (HFM) is designed to aggregate and distill information to refine spatial information and reconstruct high-quality video frames.
- 21
- 19
- 19
- Beyond the Parts: Learning Coarse-to-Fine Adaptive Alignment Representation for Person Search19
A Coarse-to-Fine Adaptive Alignment Representation (CFA2R) network for learning multiple granular features in misaligned person search in the coarse- to-fine perspective is proposed and a Part-Attentional Progressive Module (PAPM) is designed to guide the network to focus on informative body parts and positive accessorial regions.
- 18
- Progressive Spatial-temporal Collaborative Network for Video Frame Interpolation18
This work develops a content-guided motion module (CGMM) and a motion-guided content module (MGCM) for individual content and motion representation, and develops a novel progressive spatial-temporal Collaborative network (Prost-Net) for video frame interpolation.
- 18
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- 15
- 15
- 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.
- 15
- 15
- 14
- 14
- 14
- 14
- 14
- 13
- 13
- Store and Fetch Immediately: Everything Is All You Need for Space-Time Video Super-resolution13
An immediate storeand-fetch network to promote long-range correlation learning, where the stored information from the past and future can be refetched to help the representation of the current frame.
- 13
- Unsupervised Vehicle Search in the Wild13
A new vehicle search dataset is established and an unsupervised framework on this benchmark dataset is designed to generate pseudo labels for further training existing vehicle re-ID or person search models to advance the research of vehicle search.
- 12
- 12
- 12
- 12
- 11
- Rep-Mamba: Re-Parameterization in Vision Mamba for Lightweight Remote Sensing Image Super-Resolution10
- 10
- 10
- 10
- 10
- 9
- Informative Classes Matter: Towards Unsupervised Domain Adaptive Nighttime Semantic Segmentation9
An Online Informative Class Sampling (OICS) strategy to adaptively mine informative classes from the target nighttime domain according to the corresponding spectrogram mean and the class frequency via the authors' Informative Mixture of Experts framework, which outperforms state-of-the-art UDA-NSS methods by large margins on three widely-used benchmarks.
- 9
- 8
- OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning8
An Online Pseudo-Supervision and Dynamic Mutual Learning (OODML) framework that enhances pseudo-label generation and feature representation while exploring their mutual learning to improve bag-level prediction is proposed and a Dynamic Decision-Making (DDM) module is developed to harmonize explicit and implicit representations of bag information for more robust decision-making.
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 6
- 6
- Context-aware target texture perturbation attack for concealed object detection6
A novel adversarial attack method, context-aware target texture perturbation, specifically designed to fool COD models, which is effectiveness in reducing COD model performance by up to 40% while preserving the visual quality of original images is demonstrated.
- 6
- 6
- 6
- 5
- The Parables of the Mustard Seed and the Yeast: Extremely Low-Budget, High-Performance Nighttime Semantic Segmentation5
A new task focusing on exploring the potential of training strategy and framework design with limited annotation to achieve high-performance NSS, and an innovative Fragmentation Synergy Active Domain Adaptation framework (FS-ADA), which progressively broadcasts the limited annotation to the unlabeled regions, achieving high performance with a minimal annotation budget.
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- S2ML: Spatio-Spectral Mutual Learning for Depth Completion3
This work proposes a Spatio-Spectral Mutual Learning framework (S2ML) to harmonize the advantages of both spatial and frequency domains for depth completion, and considers the distinct properties of amplitude and phase spectra and devise a dedicated spectral fusion module.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- Pixel-REfocused Navigated Tri-margin for Semi-supervised Action Detection2
This paper proposes an effective pipeline called Pixel-Refocused Navigated Tri-margin (PRENT), which adaptively leverages class-explicit knowledge to manage uncertain boundaries within latent buffer regions within semi-supervised action detection.
- 2
- 2
- Multimedia Content Understanding in Harsh Environments2
This tutorial introduces some multimedia enhancement methods, presents recent advances in 2D and 3D visual scene understanding, shows strategies to estimate the prediction uncertainty, provides a brief summary, and shows some typical applications.
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- M2DAO-Talker: Harmonizing Multi-Granular Motion Decoupling and Alternating Optimization for Talking-Head Generation–
M2DAO-Talker is proposed, a novel framework integrating Multi-granular Motion decoupling and Dynamic Alternating Optimization that significantly outperforms state-of-the-art approaches both qualitatively and quantitatively.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.