Temporal Regularization Makes Your Video Generator Stronger

Harold Haodong Chen^1,2 Haojian Huang^1,4 Xianfeng Wu^1,2 Yexin Liu^1,2
Yajing Bai^1,2 Wen-Jie Shu^1,2 Harry Yang^1,2 Ser-Nam Lim^1,3
1Everlyn AI ²HKUST ³UCF ⁴HKU

Abstract

Temporal quality is a critical aspect of video generation, as it ensures consistent motion and realistic dynamics across frames. However, achieving high temporal coherence and diversity remains challenging. In this work, we explore temporal augmentation in video generation for the first time, and introduce FluxFlow for initial investigation, a strategy designed to enhance temporal quality. Operating at the data level, FluxFlow applies controlled temporal perturbations without requiring architectural modifications. Extensive experiments on UCF-101 and VBench benchmarks demonstrate that FluxFlow significantly improves temporal coherence and diversity across various video generation models, including U-Net, DiT, and AR-based architectures, while preserving spatial fidelity. These findings highlight the potential of temporal augmentation as a simple yet effective approach to advancing video generation quality.

Overview

Evaluations

CogVideoX-2B

NOVA

VideoCrafter2

BibTeX

Project page template is borrowed from DreamBooth.