Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance

2026-09-08

AI Summary

本文通过引入光谱张力诊断视频生成中的时间状态传输问题，并提出光谱传输稳态方法来修正这些问题，以提高视频的时间一致性和视觉质量。

Abstract

Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze local attention entropy, but these views do not reveal whether temporal interactions stay in a healthy transport regime. In this work, we study video generation through the perspective of Temporal State Transport. We introduce Spectral Tension, a signed diagnostic that compares local attention diffuseness with global spectral diversity, and use it to identify two opposite temporal failures: fragmented transport and over-mixing hotspots. Based on this diagnosis, we propose Spectral Transport Homeostasis, a training-free regulator that softly corrects pathological temporal states while largely preserving balanced ones. Experiments on pretrained video generation models show that the original model often occupies imbalanced temporal regimes, whereas our method selectively applies larger corrections to the worst temporal hotspots and improves temporal consistency and visual quality without finetuning. Code: https://github.com/lytang63/temporal-state-transport

Problem

• Temporal State Transport
• Spectral Tension
• Temporal Consistency
• Video Generation
• Attention Entropy

Innovation

• Temporal State Transport
• Spectral Tension
• Spectral Transport Homeostasis