Presentation

<
LayerFlow: A Unified Model for Layer-aware Video Generation
SessionVideo Generation
DescriptionWe propose LayerFlow, a unified framework for layer-aware video generation, enabling seamless creation of transparent foregrounds, clean backgrounds, and blended scenes. With multi-stage training and LoRA techniques improving layer-wise video quality with limited data, it also supports variants like video layer decomposition, generating backgrounds for given foregrounds and vice versa.
Authors
Sihui Ji
The University of Hong Kong
Hao Luo
DAMO Academy, Alibaba Group
Xi Chen
The University of Hong Kong
Yuanpeng Tu
The University of Hong Kong
Yiyang Wang
The University of Hong Kong
Hengshuang Zhao
The University of Hong Kong
Event Type
Technical Paper
TimeTuesday, 12 August 202511:25am - 11:35am 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
Tuesday, 12 August 202510:45am - 12:35pm PDTWest Building, Rooms 118-120
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationInterspatial Attention for Efficient 4D Human Video Generation
Similar Presentations
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
FashionComposer: Compositional Fashion Image Generation
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control