Presentation

<
DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution
SessionFiltering Super-Res, & Visual Quality
DescriptionIn this work, we propose DAM-VSR, an appearance and motion disentanglement framework for video super-resolution. Appearance enhancement is achieved through reference image super-resolution, while motion control is achieved through video ControlNet. Additionally, we propose a motion-aligned bidirectional sampling strategy to support the generation of long videos.
Authors
Zhe Kong
Sun Yat-sen University
Meituan
Le Li
Tianjin University
Yong Zhang
Meituan
Feng Gao
Meituan
Shaoshu Yang
School of Artificial Intelligence, University of Chinese Academy of Sciences
Tao Wang
Nanjing University
Kaihao Zhang
Harbin Institute of Technology
Zhuoliang Kang
Meituan
Xiaoming Wei
Meituan
Guanying Chen
Sun Yat-sen University
Wenhan Luo
The Hong Kong University of Science and Technology
Event Type
Technical Paper
TimeThursday, 14 August 20259:40am - 9:50am PDT
LocationWest Building, Rooms 118-120
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Thursday, 14 August 20259:00am - 10:30am PDTWest Building, Rooms 118-120
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationDC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
Similar Presentations
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
Motion Inversion for Video Customization
Dynamic Concepts Personalization from Single Videos