Improving Video Generation with Human Feedback

TL;DR

This paper enhances video generation quality by integrating human feedback through a new dataset, a reward model, and three alignment algorithms, leading to more realistic and personalized videos.

Contribution

It introduces a large-scale human preference dataset, a multi-dimensional reward model, and three novel algorithms for aligning flow-based video generation models with human preferences.

Findings

VideoReward outperforms existing reward models.

Flow-DPO surpasses other training strategies in performance.

Flow-NRG enables personalized video quality adjustments.

Abstract

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human feedback to mitigate these problems and refine the video generation model. Specifically, we begin by constructing a large-scale human preference dataset focused on modern video generation models, incorporating pairwise annotations across multi-dimensions. We then introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy. From a unified reinforcement learning perspective aimed at maximizing reward with KL regularization, we introduce three alignment algorithms for flow-based models. These include two training-time strategies: direct preference optimization for flow (Flow-DPO) and reward weighted regression for flow (Flow-RWR), and an inference-time technique, Flow-NRG, which applies reward guidance directly to noisy videos. Experimental results indicate that VideoReward significantly outperforms existing reward models, and Flow-DPO demonstrates superior performance compared to both Flow-RWR and supervised fine-tuning methods. Additionally, Flow-NRG lets users assign custom weights to multiple objectives during inference, meeting personalized video quality needs.