Abstract
Flow-matching-based multi-view world models generate realistic videos, but are commonly restricted to fixed camera rigs. Extending them to continuously varying camera poses requires paired pose--video observations with dense pose coverage, which are costly to acquire. We introduce \emph{SymRegFlow}, a symmetry-regularized flow-matching framework for multi-view-consistent video generation across continuous viewpoints without ground-truth novel-view RGB supervision. For each target pose, SymRegFlow geometrically warps source views into noisy anchors and combines masked dual-anchor supervision with cross-anchor denoising-output consistency to mitigate anchor-specific errors. Under an affine Gaussian surrogate, we prove that suitable consistency regularization recovers the clean-reference optimum at fixed noise levels, strictly outperforming single- and merged-anchor baselines. Experiments on Cosmos-Drive-Dreams and nuScenes demonstrate high-quality, multi-view-consistent autonomous-driving video generation: on nuScenes, SymRegFlow achieves the lowest FVD and FVMD among the evaluated baselines, reducing FVD by over 31\% relative to the best baseline, and source-conditioned inference also attains the best FID and instance preservation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ye, X., Wang, Y., Liu, X., Wang, J., Xu, Y., Wang, R., Chen, W., Su, D., & Zhu, J. (2026). SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models. https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models
MLA 9
Ye, Xi, et al. "SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models." https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models.
Chicago (author–date)
Ye, Xi, Yuzhu Wang, Xiaoyang Liu, Jiayi Wang, Yangyang Xu, Ruyu Wang, Wenlin Chen, Duo Su, and Jun Zhu. 2026. "SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models." https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models.
Harvard
Ye, X., Wang, Y., Liu, X., Wang, J., Xu, Y., Wang, R., Chen, W., Su, D. and Zhu, J. (2026) 'SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models', Available at: https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models.
Vancouver
Ye X, Wang Y, Liu X, Wang J, Xu Y, Wang R, et al. SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models. https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models
IEEE
X. Ye, Y. Wang, X. Liu, J. Wang, Y. Xu, R. Wang, W. Chen, D. Su, and J. Zhu, "SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models," https://omanscience.com/en/articles/symregflow-symmetry-regularized-flow-matching-for-video-world-models.