Publications

Pair2Point: Distilling Pairwise Reasoning into Pointwise Rewards for High-Quality Text-to-Image Generation

Qian Wang, Xinhang Leng, Yinan Li, Sujie Hu, Huaisong Zhang, Chen Li, Jian Zhang

Under Review 2027

A two-stage reward modeling paradigm that trains a pairwise comparison model and distills it into an efficient pointwise scorer, with corresponding benchmarks and preference datasets.

AgentKE: Agentic Knowledge Editing for Diffusion Transformers

Qian Wang, Shuyu Wang, Zhile Guan, Xinhua Cheng, Xiandong Meng, Jian Zhang

Under Review 2027

An agentic knowledge-editing framework for text-to-image DiTs that decomposes natural-language intents with a VLM, edits linear projection layers in the protection-set null space, and reflects on the editing results.

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

Qian Wang, Yu Wang, Weiqi Li, Xinhua Cheng, Xiandong Meng, Ronggang Wang, Jian Zhang

European Conference on Computer Vision (ECCV) 2026

Uses two diffusion models to extract structure from low-quality novel views and appearance from reference views, with a reliability-enhanced Render-Refine-Optimize loop for sparse-view 3DGS.

OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation

Weiqi Li, Shijie Zhao, Chong Mou, Xuhan Sheng, Zhenyu Zhang, Qian Wang, Junlin Li, Li Zhang, Jian Zhang

International Journal of Computer Vision (IJCV) 2026

Enables motion control for omnidirectional image-to-video generation.

Paper

Garment De-Warping for Virtual Try-On in the Wild

Yu Gu, Jiexuan Zhang, Qian Wang, Jian Zhang

2025 IEEE International Conference on Image Processing (ICIP) 2025

AlignedGen: Aligning Style Across Generated Images

Jiexuan Zhang, Yiheng Du, Qian Wang, Weiqi Li, Yu Gu, Jian Zhang

Advances in Neural Information Processing Systems (NeurIPS) 2025

Aligns visual style across a set of generated images.

Paper

OD-VAE: An Omni-Dimensional Video Compressor for Improving Latent Video Diffusion Model

Liuhan Chen, Zongjian Li, Bin Lin, Bin Zhu, Qian Wang, Shenghai Yuan, Xing Zhou, Xinhua Cheng, Li Yuan

2025 IEEE International Conference on Multimedia and Expo (ICME) 2025

Mind-Edit: MLLM Insight-Driven Editing via Language-Vision Projection

Shuyu Wang, Weiqi Li, Qian Wang, Shijie Zhao, Jian Zhang

arXiv preprint arXiv:2505.19149 2025

Paper

Prompt2Poster: Automatically Artistic Chinese Poster Creation from Prompt Only

Shaodong Wang, Yunyang Ge, Liuhan Chen, Haiyang Zhou, Qian Wang, Xinhua Cheng, Li Yuan

ACM International Conference on Multimedia (ACM MM) 2024

An automatic poster creation framework that uses an LLM to extract user intention from prompts and generate an aligned background.

Paper

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

Qian Wang, Weiqi Li, Chong Mou, Xinhua Cheng, Jian Zhang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

A controllable panoramic video generation method with the WEB360 dataset, supporting text and dense optical flow as motion conditions.

NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results

Mingdeng Cao, Chong Mou, Fanghua Yu, Xintao Wang, Yinqiang Zheng, Jian Zhang, Chao Dong, Gen Li, Ying Shan, Qian Wang, others

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023

A spatial-temporal two-stage model for omnidirectional image and video super-resolution in the NTIRE 2023 challenge.

Paper

Panoptic Compositional Feature Field for Editable Scene Rendering with Network-Inferred Labels via Metric Learning

Xinhua Cheng, Yanmin Wu, Mengxi Jia, Qian Wang, Jian Zhang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Uses metric learning to leverage 2D network-inferred labels for discriminating feature fields, enabling 3D segmentation and editing.

Paper

Deep Generalized Unfolding Networks for Image Restoration

Chong Mou, Qian Wang, Jian Zhang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022

Integrates a gradient estimation strategy into proximal gradient descent, enabling unfolding networks to handle complex real-world degradations.

PaperCode

More is Better: Multi-Source Dynamic Parsing Attention for Occluded Person Re-Identification

Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang

ACM International Conference on Multimedia (ACM MM) 2022

Introduces multi-source knowledge ensemble in occluded person re-ID to leverage external semantic cues from different domains.

Paper

A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition

Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2022

Models pedestrian attribute recognition as a multimodal problem and captures intra- and cross-modal correlations with a simple visual-textual baseline.

PaperCode

Detection Features as Attention (Defat): A Keypoint-Free Approach to Amur Tiger Re-Identification

Xinhua Cheng, Jianing Zhu, Nan Zhang, Qian Wang, Qijun Zhao

2020 IEEE International Conference on Image Processing (ICIP) 2020

DOI