The authors propose a fine-tuning method for pretrained multi-view world models.
Symmetry-regularized flow matching enables video generation from any camera pose without ground truth novel views
The method uses masked dual-anchor supervision and cross-anchor denoising consistency to produce multi-view consistent videos for autonomous driving
Top University
Xi Ye · Yuzhu Wang · Xiaoyang Liu · Jiayi Wang · Yangyang Xu · Ruyu Wang · +3 more
Tsinghua University · Robert Bosch GmbH · Bosch (China) Investment Ltd. · University of Chinese Academy of Sciences
Research Digest··2 min read
Thread:Video Diffusion Scaling
The authors introduce SymRegFlow, a flow-matching framework that generates multi-view-consistent video from continuous camera poses without requiring paired novel-view RGB supervision.
Why this paper
From University of Chinese Academy of Sciences and 3 others · Part of Video Diffusion Scaling, now 4 papers
In one line
SymRegFlow generates multi-view consistent videos across continuous viewpoints without novel-view RGB supervision, using masked dual-anchor supervision and cross-anchor denoising consistency.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§