DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking
英文标题：DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking
arXiv:2607.18664v1 Announce Type: new Abstract: Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesi
打开原文相关 4 · 机会 0
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
中文
arXiv:2607.18664v1 Announce Type: new Abstract: Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesi
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×