韩镇｜武汉大学｜学者主页

2026

Wan-Image: Pushing the Boundaries of Generative Visual Intelligence

Chao-Jie Mao, Chenjun Xie, Chongyang Zhong, Haoyou Deng, Jia-Xing Zhao, Jie Xiao, Jin-Bo Xing, Jing-Feng Zhang, Jing-Ren Zhou, Jing-Yi Zhang, Jun Dan, Kai Zhu, Kang Zhao, Keyu Yan, Ming-Hui Chen, Pan Li, Shuang Chen, Tong Shen, Yu Liu, Yue Jiang, Yulin Pan, Yuxiang Tuo, Zeyinzi Jiang, Zhen Han, Ang Wang, Bang Zhang, Bao-Le Ai, Bin Wen, Bo Feng, Fei Yu, Gang Wang, Hai-Ming Zhao, Henel Kang, Jianjing Xiang, Jia-Wei Zeng, Jinkai Wang, Jun-Jie Zhou, Ke Sun, Lin-Han Wu, Peihao Gong, Ping Wu, Rui Wu, Tongtong Su, Wen-Meng Zhou, Wenting Shen, Wen-Yuan Yu, Xiang Xu, Xiaoming Huang, Xiejie Shen, Xin Xu, Yan Kou, Yan-Mei Lv, Y. Zhai, Yitong Huang, Yun Zheng, Yuntao Hong, Zhe Zhang, Zhi-Cheng Zhang

2026

Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training

Jin-Bo Xing, Zeyinzi Jiang, Yuxiang Tuo, Chao-Jie Mao, Xiaotang Gai, Xi Chen, Jing-Feng Zhang, Yulin Pan, Zhen Han, Jie Xiao, Keyu Yan, Chen-Wei Xie, Chongyang Zhong, Kai Zhu, Tong Shen, Liang-Hua Huang, Yu Liu, Yu-Jiu Yang

arXiv.org

精选作品

期刊论文

Wan-Image: Pushing the Boundaries of Generative Visual Intelligence

Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training

GaitFuse: A hierarchical cross-modal alignment and uncertainty-aware fusion framework for multi-modal gait recognition

An angle-guided bidirectional feature transformation network for multi-frame tilt-angle face recognition

CMVF: Cross-modal unregistered video fusion via spatio-temporal consistency

Improving the Generalization of Gait Recognition with Limited Datasets

AUGDet: Audio-Guided Diffusion Model for Visual Feature Restoration in Low-Visibility Object Detection

Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset

ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editing

VACE: All-in-One Video Creation and Editing

ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling

IDRetracor: Towards Visual Forensics against Malicious Face Swapping

Multimodal Re-Ranking for Heterogeneous Face Re-Identification

Image deraining via dual-level contextual information associated learning for autonomous driving

Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation

Multi-Stage Statistical Texture-Guided GAN for Tilted Face Frontalization

StyleBooth: Image Style Editing with Multimodal Instruction

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer

Locate, Assign, Refine: Taming Customized Image Inpainting with Text-Subject Guidance

Adversarial intensity awareness for robust object detection

Cross-Modal Face Super-Resolution Based on Quasi-Siamese Domain Transfer Fusion Network

Few-Shot Face Sketch-to-Photo Synthesis via Global-Local Asymmetric Image-to-Image Translation

Dual-Domain Multi-Model GAN Fingerprint Restoration for Compressed Fake Face Attribution

Implicit Mutual Learning With Dual-Branch Networks for Face Super-Resolution

Unlabeled Data Assistant: Improving Mask Robustness for Face Recognition

Unconventional Face Adversarial Attack

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

Learning Degradation for Real-World Face Super-Resolution

Implicit space pose consistent transfer network for deep face verification

Deepfake Face Provenance for Proactive Forensics

DeepReversion: Reversely Inferring the Original Face from the DeepFake Face

HeadPose-Softmax: Head pose adaptive curriculum learning loss for deep face recognition

Stylized image denoising via noise style transfer and Quasi Siamese network

LSA3D: Lightweight Separate Asynchronous 3D Convolutional Neural Network for Gait Recognition

Multi-frame Tilt-angle Face Recognition Using Fusion Re-ranking

Local Eyebrow Feature Attention Network for Masked Face Recognition

Joint Segmentation and Identification Feature Learning for Occlusion Face Recognition

Realistic frontal face reconstruction using coupled complementarity of far-near-sighted face images

Real-Time Video Deraining via Global Motion Compensation and Hybrid Multi-Scale Temporal Correlations

Face Super-Resolution with Better Semantics and More Efficient Guidance

Video Similarity and Alignment Learning on Partial Video Copy Detection

Multi-Scale Hybrid Fusion Network for Single Image Deraining

A Tilt-Angle Face Dataset And Its Validation

Adaptive Texture Distillation Network for Image Hybrid Super-Resolution

When Face Recognition Meets Occlusion: A New Benchmark

Low-quality watermarked face inpainting with discriminative residual learning

Multi-Stage Degradation Homogenization for Super-Resolution of Face Images With Extreme Degradations

“One-Shot” Super-Resolution via Backward Style Transfer for Fast High-Resolution Style Transfer

多源数据行人重识别研究综述

Decomposition Makes Better Rain Removal: An Improved Attention-Guided Deraining Network

Single image de-raining via clique recursive feedback mechanism

Image Super-Resolution Using Residual Global Context Network

Video-Based Person Re-Identification With Unregulated Sequences

Ultra-dense GAN for satellite imagery super-resolution

GAN-Based Multi-level Mapping Network for Satellite Imagery Super-Resolution

Modeling and Optimizing of the Multi-Layer Nearest Neighbor Network for Face Image Super-Resolution

S3D: Scalable Pedestrian Detection via Score Scale Surface Discrimination

Adaptive Aggregation Network for Face Hallucination

H.264 based screen content coding with HSV quantization

Fast video enhancement transcoding

Face Super Resolution for VLQ facial images via parent patch matching

Face super resolution based on parent patch prior for VLQ scenarios

HRM graph constrained dictionary learning for face image super-resolution

A novel face super resolution approach for noisy images using contour feature and standard deviation prior

Face Image Super-Resolution Through Improved Neighbor Embedding

A Stepwise Frontal Face Synthesis Approach for Large Pose Non-frontal Facial Image

Heteroskedasticity tuned mixed-norm sparse regularization for face hallucination

Facial Image Hallucination Through Coupled-Layer Neighbor Embedding

Deep Feature Representation via Multiple Stack Auto-Encoders

Person Re-identification via Attribute Confidence and Saliency

图约束字典和加权稀疏表示人脸超分辨率算法

Coupled Discriminant Multi-Manifold Analysis with Application to Low-Resolution Face Recognition

Gabor-based patch covariance matrix for face sketch synthesis

Face Super-Resolution via Multilayer Locality-Constrained Iterative Neighbor Embedding and Intermediate Dictionary Learning

Face Hallucination via Trend-Constrained Regularization

Efficient learning based face hallucination approach via facial standard deviation prior

Noise Robust Face Hallucination via Locality-Constrained Representation

Face image super-resolution through locality-induced support regression