PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiong, Zhexiao, Song, Yizhi, He, Liu, Xiong, Wei, Yuan, Yu, Qiao, Feng, Jacobs, Nathan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.13770