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
- Jian ZhangSuggested from co-authorship
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works30 from public data
- 923
- Deep Generalized Unfolding Networks for Image Restoration338
A Deep Generalized Unfolding Network (DGUNet) for image restoration by integrating a gradient estimation strategy into the gradi-ent descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation.
- DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models241
A novel image editing method, DragonDiffusion, enabling Drag-style manipulation on Diffusion models, that can transform the editing signals into gradients via feature correspondence loss to modify the intermediate representation of the diffusion model.
- 178
- DiffEditor: Boosting Accuracy and Flexibility on Diffusion-Based Image Editing114
In this paper, DiffEditor is proposed to rectify two weaknesses in existing diffusion-based image editing: in complex scenarios, editing results often lack editing accuracy and exhibit unexpected artifacts; and lack of flexibility to harmonize editing operations, e.g., imagine new content.
- Dynamic Attentive Graph Learning for Image Restoration111
This paper proposes an improved graph model to perform patch-wise graph convolution with a dynamic and adaptive number of neighbors for each node, so that image content can adaptively balance over-smooth and over-sharp artifacts through the number of its connected neighbors, and thePatch-wise non-local correlations can enhance the message passing process.
- Optimization-Inspired Cross-Attention Transformer for Compressive Sensing108
This paper proposes an Optimization-inspired Cross-attention Transformer module as an iterative process, leading to a lightweight OCT-based Unfolding Framework (OCTUF) for image CS, which achieves superior performance compared to state-of-the-art methods while training lower complexity.
- DreamO: A Unified Framework for Image Customization97
This paper presents DreamO, an image customization framework designed to support a wide range of tasks while facilitating seamless integration of multiple conditions, and utilizes a diffusion transformer (DiT) framework to uniformly process input of different types.
- Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging84
A novel dense deep unfolding network (DUN) with 3D-CNN prior with a dense feature map adaption (DFMA) module to allow inter-phase information to fuse adaptively and to promote network robustness.
- 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model78
This paper introduces a lightweight 360-Adapter accompanied by 360 Enhancement Techniques to transform pre-trained T2V models for panorama video generation and proposes a new panorama dataset named WEB360 consisting of panoramic video-text pairs for training 360DVD, addressing the absence of captioned panoramic video datasets.
- Large-Capacity and Flexible Video Steganography via Invertible Neural Network73
A Large-capacity and Flexible Video Steganography Network (LF-VSN) that has high security, large hiding capacity, and flexibility, and a scalable strategy in multiple videos hiding, which can hide variable numbers of secret videos in a cover video with a single model and a single training session.
- MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution61
A metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner and introduces an anchor point strategy in the metric learning process to normalize the distribution of metric space.
- 47
- 47
- NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results43
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results, and gauge the state of the art of video quality enhancement.
- TransCL: Transformer Makes Strong and Flexible Compressive Learning38
The proposed TransCL can achieve state-of-the-art performance in image classification and semantic segmentation tasks and can obtain almost the same performance as when operating directly on the original data and can still obtain satisfying performance even with an extremely low CS ratio.
- 12
- 8
- OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation7
OmniDrag, the first approach enabling both scene- and object-level motion control for accurate, high-quality omnidirectional image-to-video generation, is proposed and an omnidirectional control module is introduced, which is jointly fine-tuned with temporal attention layers to effectively handle complex spherical motion.
- 7
- 5
- 5
- 4
- 2
- Consistent Human Image and Video Generation with Spatially Conditioned Diffusion1
By fine-tuning existing base diffusion models on human video data, the method demonstrates strong generalization to unseen human identities and poses without requiring additional per-instance fine-tuning, and ensures flexible control over the appearance of generated human images and videos.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.