Pengfei Wan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pengfei Wan has a total of 172 co-authors. Here are the top co-authors by number of shared publications:
- Di Zhang
Kuaishou Technology, Beijing, China
9 shared publications - Chongyang Ma
Kuaishou Technology, Beijing, China
8 shared publications - Haibin Huang
Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China
7 shared publications - Xiaoqiang Liu
Kuaishou Technology, Beijing, China
4 shared publications - Yan Zhou
Kuaishou Technology, Beijing, China
4 shared publications - Bohan Zeng
Peking University, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4337-4346
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4337-4346
Open AccessHuman-Centric Image Captioning with Subject-Centered Spatial Understanding
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14992-15001
VC-Agent: An Interactive Agent for Customized Video Dataset Collection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14992-15001
Open AccessVC-Agent: An Interactive Agent for Customized Video Dataset Collection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7670-7679
CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7670-7679
Open AccessCineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10730-10739
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10730-10739
Open AccessSubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
- 12 September 2026
- Published by Springer Nature
- p. 451-469
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
- 12 September 2026
- Published by Springer Nature
- p. 451-469
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessCameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 7031-7045
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting
Video inpainting modifies local regions in video while ensuring spatial and temporal coherence. However, existing methods-both traditional and recent diffusion-based ones-face key limitations: they lack unified support for both insertion and completion, and are restricted to single-object inpainting, making it difficult to handle multi-object scenarios involving grounding and interaction. In this article, we propose MultiPaint, a unified framework for multi-task, multi-object, and multi-condition video inpainting. First, we introduce dual-branch adapters to unify the insertion and completion tasks within a single model. Moreover, we propose a test-time scheduled feature composition strategy that enables multi-object inpainting with user-specified locations while better preserving interactions among objects, a setting that has been insufficiently addressed in prior work. Additionally, we introduce a multi-condition inpainting scheme that integrates text-guided, image-guided, and keyframe-guided modes via dynamic frame masking, providing more controllability in appearance customization. Extensive experiments show that MultiPaint achieves state-of-the-art performance on object insertion and scene completion among the recent works. We further demonstrate its versatility in downstream tasks including grounded video generation, object editing, object removal, image-guided inpainting, and long video inpainting.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 7031-7045
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting
Video inpainting modifies local regions in video while ensuring spatial and temporal coherence. However, existing methods-both traditional and recent diffusion-based ones-face key limitations: they lack unified support for both insertion and completion, and are restricted to single-object inpainting, making it difficult to handle multi-object scenarios involving grounding and interaction. In this article, we propose MultiPaint, a unified framework for multi-task, multi-object, and multi-condition video inpainting. First, we introduce dual-branch adapters to unify the insertion and completion tasks within a single model. Moreover, we propose a test-time scheduled feature composition strategy that enables multi-object inpainting with user-specified locations while better preserving interactions among objects, a setting that has been insufficiently addressed in prior work. Additionally, we introduce a multi-condition inpainting scheme that integrates text-guided, image-guided, and keyframe-guided modes via dynamic frame masking, providing more controllability in appearance customization. Extensive experiments show that MultiPaint achieves state-of-the-art performance on object insertion and scene completion among the recent works. We further demonstrate its versatility in downstream tasks including grounded video generation, object editing, object removal, image-guided inpainting, and long video inpainting.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 6305-6318
ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis
Audio-driven human gesture synthesis is a crucial task with broad applications in virtual avatars, human-computer interaction, and creative content generation. Despite notable progress, existing methods often produce coarse gestures, lack expressiveness, and fail to fully align with audio semantics. To address these challenges, we propose ExGes, a novel retrieval-enhanced diffusion framework with three key designs: (1) a Motion Base Construction, which builds a gesture library from the training dataset; (2) a Motion Retrieval Module, employing contrastive learning and momentum distillation for retrieving fine-grained reference poses; and (3) a Precise Control Module, integrating partial masking and stochastic masking to enable flexible and fine-grained control. Experimental evaluations on BEAT2 demonstrate that ExGes reduces Fréchet Gesture Distance by 4.55%and improves motion diversity by 5.3% over EMAGE, with user studies revealing a 71.3% preference for its naturalness and semantic relevance.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 6305-6318
ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis
Audio-driven human gesture synthesis is a crucial task with broad applications in virtual avatars, human-computer interaction, and creative content generation. Despite notable progress, existing methods often produce coarse gestures, lack expressiveness, and fail to fully align with audio semantics. To address these challenges, we propose ExGes, a novel retrieval-enhanced diffusion framework with three key designs: (1) a Motion Base Construction, which builds a gesture library from the training dataset; (2) a Motion Retrieval Module, employing contrastive learning and momentum distillation for retrieving fine-grained reference poses; and (3) a Precise Control Module, integrating partial masking and stochastic masking to enable flexible and fine-grained control. Experimental evaluations on BEAT2 demonstrate that ExGes reduces Fréchet Gesture Distance by 4.55%and improves motion diversity by 5.3% over EMAGE, with user studies revealing a 71.3% preference for its naturalness and semantic relevance.
- Top Cited PapersOpen Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Top Cited PapersOpen AccessContext as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessCamCloneMaster: Enabling Reference-based Camera Control for Video Generation