Presentation

<
Generative Video Matting
SessionVideo Generation
DescriptionLimited high-quality ground-truth data hinders traditional video matting's real-world application. This work tackles this by advocating for large-scale training with diverse synthetic segmentation and matting data. A novel generative pipeline is also introduced to predict temporally consistent alpha masks with fine-grained details.
Authors
Yongtao Ge
The University of Adelaide
Zhejiang University
Kangyang Xie
Zhejiang University
Guangkai Xu
Zhejiang University
Mingyu Liu
Zhejiang University
Li Ke
Alibaba Group
Longtao Huang
Alibaba Group
Hui Xue
Alibaba Group
Hao Chen
Zhejiang University
Chunhua Shen
Zhejiang University of Technology
Zhejiang University
Event Type
Technical Paper
TimeTuesday, 12 August 202511:45am - 11:55am 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
Not Livestreamed
Not Recorded
Next PresentationNext PresentationVideo Generation - Interactive Discussion
Similar Presentations
LayerFlow: A Unified Model for Layer-aware Video Generation
DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control