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
- Qionghai DaiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works233 from public data
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks5,700
This work proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections, and proposes a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels.
- Residual Dense Network for Image Super-Resolution4,162
This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way.
- 1,955
- CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion990
A novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network that achieves promising results in multiple fusion tasks, including infrared- visible image fusion and medical image fusion, and can boost the performance in downstream infrared-visible semantic segmentation and object detection in a unified benchmark.
- Residual Dense Network for Image Restoration895
This work proposes residual dense block (RDB) to extract abundant local features via densely connected convolutional layers and proposes local feature fusion in RDB to adaptively learn more effective features from preceding and current local features and stabilize the training of wider network.
- Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement881
A simple yet principled One-stage Retinex-based Framework (ORF), designed an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions, and obtains the algorithm, Retinexformer.
- TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution655
Experimental results demonstrate that theTDAN is capable of alleviating occlusions and artifacts for temporal alignment and the TDAN-based VSR model outperforms several recent state-of-the-art VSR networks with a comparable or even much smaller model size.
- GAN Inversion: A Survey653
This paper provides a survey of GAN inversion with a focus on its representative algorithms and its applications in image restoration and image manipulation, and discusses the trends and challenges for future research.
- Visual Semantic Reasoning for Image-Text Matching625
A simple and interpretable reasoning model to generate visual representation that captures key objects and semantic concepts of a scene that outperforms the current best method for image retrieval and caption retrieval on MS-COCO and Flickr30K datasets.
- DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion480
This work proposes a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) that can generate high-quality fused images with natural image generative priors and cross-modality information from source images.
- DiffIR: Efficient Diffusion Model for Image Restoration476
This work proposes an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising network, which can adopt a joint optimization of CPENS2, DIRformer, and denoising network, which can further reduce the estimation error influence.
- Dual Aggregation Transformer for Image Super-Resolution454
A novel Transformer model, Dual Aggregation Transformer (DAT), is proposed, which aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction423
A novel framework, Mask-guided Spectral-wise Transformer (MST), that treats each spectral feature as a token and calculates self-attention along the spectral dimension and significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs.
- 405
- LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block367
A lightweight SR model, LatticeNet, is proposed, which uses series connection of LBs and the backward feature fusion, which can achieve superior accuracy on four available benchmark datasets against other state-of-the-art methods, while maintaining relatively low computation and memory requirements.
- MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction364
This work proposes a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction that significantly outperforms other state-of-the-art methods.
- Adversarial Feature Hallucination Networks for Few-Shot Learning324
Adversarial Feature Hallucination Networks (AFHN) is proposed which is based on conditional Wasserstein Generative Adversarial networks (cWGAN) and hallucinates diverse and discriminative features conditioned on the few labeled samples and comparative results substantiate the superiority of AFHN to existing data augmentation based FSL approaches and other state-of-the-art ones.
- 307
- Equivariant Multi-Modality Image Fusion299
This work proposes the Equivariant Multi-Modality imAge fusion (EMMA) paradigm, a novel training paradigm that encompasses a fusion module, a pseudo-sensing module, and an equivariant fusion module that enables the net training to follow the principles of the natural sensing-imaging process while satisfying the equivariant imaging prior.
- Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis270
Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability.
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging250
A high-resolution dual-domain learning network (HDNet) for HSI reconstruction with HR pixel-level attention and frequency-level refinement that achieves SOTA performance on simulated and real HSI datasets.
- MambaIRv2: Attentive State Space Restoration229
This work proposes MambaIRv2, which equips Mamba with the non-causal modeling ability similar to ViTs to reach the attentive state space restoration model, and introduces a semantic-guided neighboring mechanism to encourage interaction between distant but similar pixels.
- Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution214
A one-stage space-time video super-resolution framework is proposed, which directly synthesizes an HR slow-motion video from an LFR, LR video and proposes a deformable ConvLSTM to align and aggregate temporal information simultaneously for better leveraging global temporal contexts.
- 189
- 172
- Accurate Image Restoration with Attention Retractable Transformer169
Attention Retractable Transformer (ART) is proposed for image restoration, which presents both dense and sparse attention modules in the network, which greatly enhances representation ability of Transformer while providing retractable attention on the input image.
- Diffusion Models in Low-Level Vision: A Survey158
This paper presents the first comprehensive review focused on denoising diffusion models applied to low-level vision tasks, covering both theoretical and practical contributions, and highlights the limitations of current diffusion models and proposes four promising directions for future research.
- 153
- 149
- Pyramid Attention Network for Image Restoration142
A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels.
- Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution138
A dynamic high-pass filtering module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals and a matrix multi-spectral channel attention module that predicts the attention map of features decomposed in the frequency domain.
- Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising134
This paper proposes a spectral enhanced rectangle Trans-former, driving it to explore the nonlocal spatial similarity and global spectral low-rank property of HSIs, and designs a spectral enhancement module that is capable of extracting global underlying low- rank property of spatial-spectral cubes to suppress noise.
- Complexity Experts are Task-Discriminative Learners for Any Image Restoration128
The proposed MoCE-IR model outperforms state-of-the-art methods, affirming its efficiency and practical applicability and introducing “complexity experts” – flexible expert blocks with varying computational complexity and receptive fields.
- CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution123
This paper explicitly design an implicit attention network to learn the ensemble weights for the nearby local features in a continuous implicit attention-in-attention network, called CiaoSR, which significantly outperforms the existing single image SR methods with the same backbone.
- 117
- 117
- 107
- No One Left Behind: Real-World Federated Class-Incremental Learning102
A proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients, and a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss are developed.
- LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising99
A novel method called LG-BPN is presented, which takes the spatial correlation statistic into the authors' network design for local detail restoration, and also brings the long-range dependencies modeling ability to previously CNN-based BSN methods.
- Multimodal Style Transfer via Graph Cuts97
This paper introduces a more flexible and general universal style transfer technique: multimodal style transfer (MST), which explicitly considers the matching of semantic patterns in content and style images.
- 96
- 95
- 92
- 92
- 88
- MuRF: Multi-Baseline Radiance Fields86
Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view syn-thesis under multiple different baseline settings, achieves state-of-the-art performance across multiple different baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes.
- 86
- Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction86
A Pixel Adaptive Deep Unfolding Transformer (PADUT) for HSI reconstruction is proposed, and the Non-local Spectral Transformer (NST) is introduced to emphasize the 3D characteristics of HSI for recovering.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation84
The problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression is addressed and Iterative Multi-modal Interaction (IMI) is proposed to allow continuous and in-depth interactions between language and vision features.
- NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results83
This paper reviews the NTIRE 2024 challenge on image super-resolution (×4), highlighting the solutions proposed and the outcomes obtained, and offers a comprehensive overview of current trends in this field.
- Recent Advances on Neural Network Pruning at Initialization83
A generic formulation of neural network pruning, followed by the major classic pruning topics, and a thorough and structured literature review of PaI methods is presented, consisting of two major tracks (sparse training and sparse selection).
- Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training81
Qualitative validation shows that noise generated by PNGAN is highly similar to real noise in terms of intensity and distribution, and an efficient architecture Simple Multi-scale Network (SMNet) as the generator is presented.
- Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing78
A novel Mutual Information-driven Triple interaction Network (MITNet) based on spatial-frequency dual domain information and two-stage architecture is proposed and an Adaptive Triple Interaction Module (ATIM) is developed to facilitate the information exchange between two stages.
- 75
- 72
- 70
- 69
- Cross-Modality High-Frequency Transformer for MR Image Super-Resolution68
An early effort to build a Transformer-based MR image super-resolution framework, with careful designs on exploring valuable domain prior knowledge, and establishes a novel Transformer architecture, called Cross-modality high-frequency Transformer (Cohf-T), to introduce such priors into super-resolving the low-resolution MR images.
- ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation68
Enhanced Categorical Alignment and Consistency Learning (ECACL) is proposed, a holistic SSDA framework that incorporates multiple mutually complementary domain alignment techniques and achieves fairly comprehensive domain alignments that are much better than the existing methods.
- 65
- RUN: Reversible Unfolding Network for Concealed Object Segmentation64
The Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains through a theoretically grounded framework, enabling accurate segmentation and highlighting the potential of unfolding-based frameworks for COS and other high-level vision tasks.
- 64
- Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution64
The Spherical Space feature Decomposition Network (SSDNet) is proposed to solve the above issues and can achieve state-of-the-art results on four test datasets, as well as generalize to real-world scenes.
- 64
- 59
- 59
- 58
- 53
- 52
- See More Details: Efficient Image Super-Resolution by Experts Mining51
This work introduces SeemoRe, an efficient SR model employing expert mining, strategically incorporates experts at different levels, adopting a collaborative methodology, allowing the model to achieve an optimal performance with minimal computational costs in efficient settings.
- 48
- 47
- 47
- 45
- 44
- 42
- Joint Super-Resolution and Alignment of Tiny Faces41
The proposed joint alignment and SR network to simultaneously detect facial landmarks and super-resolve tiny faces and recovers sharper edges and more details from LR face images than other state-of-the-art methods, which is demonstrated qualitatively and quantitatively.
- Structured Sparsity Learning for Efficient Video Super-Resolution40
In SSL, a structured pruning scheme called Structured Sparsity Learning (SSL) is developed according to the properties of VSR, which can significantly outperform recent methods quantitatively and qualitatively.
- Meta-Learning-Based Degradation Representation for Blind Super-Resolution38
An implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth is proposed by a Meta-Learning based Region Degradation Aware SR Network (MRDA).
- 36
- Support Neighbor Loss for Person Re-Identification36
Support neighbor (SN) loss is proposed, a new loss calculated based on the positive and negative support neighbor sets of each anchor sample, which contain more valuable contextual information and neighborhood structure that are beneficial for more stable performance.
- 35
- 33
- 32
- Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution31
This work introduces a novel approach to craft training degradation distributions using a small set of reference images based upon the binned representation of the degradation space and the Fr\'echet distance between degradation distributions.
- Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration30
This work proposes an unsupervised flow-aligned sequence-to-sequence model (S2SVR), which shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement.
- 30
- 30
- NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results29
This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.
- 29
- 28
- 28
- 27
- 27
- 27
- 26
- 25
- 25
- 24
- 24
- 24
- 24
- NTIRE 2025 Challenge on Image Super-Resolution ($\times 4$): Methods and Results23
The NTIRE 2025 image super-resolution ($\times 4$) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025, aims to recover high-resolution images from low-resolution counterparts generated through bicubic downsampling with a $\times 4$ scaling factor.
- 23
- 23
- 23
- 22
- 22
- 21
- 19
- 18
- Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment17
This work introduces a new image quality assessment (IQA) task paradigm, **grounding-IQA**, which integrates multimodal referring and grounding with IQA to realize more fine-grained quality perception, thereby extending existing IQA.
- 17
- 16
- 16
- 15
- 15
- 14
- 14
- 14
- 13
- 13
- 13
- Efficient Degradation-aware Any Image Restoration12
Extensive comparisons demonstrate that the DaAIR outperforms both state-of-the-art All-in-One models and degradation-specific counterparts, affirming the efficacy and practicality of this efficient restorer integrating holistic and specific learning within a unified model.
- 12
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- Adjustable Memory-efficient Image Super-resolution via Individual Kernel Sparsity6
This work essentially provides a dynamic parameter reassignment scheme with a given resource budget for an off-the-shelf SR model and demonstrates that IKS imparts considerable sparsity with negligible effect on SR quality.
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment4
PASTA, a novel Progressively Aggregated Spatio-Temporal Alignment framework for HDR deghosting achieves effectiveness and efficiency by harnessing hierarchical representation during feature distanglement and substantially boosts computational speed and optimizes the HDR imaging workflow.
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- Efficient image dehazing with synergic expert modulation1
A synergic expert modulation network is constructed by inserting SEM-based building blocks into the U-Net architecture to increase efficiency and achieve state-of-the-art performance on multiple datasets for the image dehazing task while incurring lower computational costs.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.