Scholar
Jinbo Xing
Google Scholar ID: ZB0gLU0AAAAJ
The Chinese University of Hong Kong
Citations & Impact
Citations
1,652
H-index
14
i10-index
16
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation, SIGGRAPH 2025 – A unified camera and object motion control framework for DiT-based image-to-video diffusion models
- Training-Free Efficient Video Generation via Dynamic Token Carving (Jenga), NeurIPS 2025 – Accelerates HunyuanVideo by 4.68–10.35× via dynamic attention carving and progressive resolution generation
- TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models, ICCV 2025 (Oral) – Generates high-fidelity novel views from monocular videos with exact pose control
- OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions, NeurIPS 2025 – Introduces a data pipeline and DiT-based method for controllable subject-driven video customization
- ToonCrafter: Generative Cartoon Interpolation, SIGGRAPH Asia 2024 (Journal Track, featured in Technical Papers Trailer) – Tames large-scale video diffusion models for cartoon interpolation
- DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors, ECCV 2024 (Oral) – Animates open-domain images using video diffusion priors
- Contributed to PICABench, Follow-Your-Creation, and Generating Past and Future in Digital Painting Processes
