基于行列式点过程引导策略优化的多样化视频生成

摘要

尽管当前文本到视频（T2V）扩散模型在生成质量和提示对齐方面取得了显著成果，但在从单一文本提示中采样多个视频时往往输出多样性不足。我们将此问题建模为集合级策略优化任务，旨在训练能够覆盖给定提示下多种合理结果的策略。为此，我们提出DPP-GRPO这一创新框架，通过结合行列式点过程（DPP）与群组相对策略优化（GRPO）理论，对多样化生成结果施加显式奖励。该框架通过DPP对冗余样本施加收益递减约束，同时利用GRPO对候选集进行群组反馈，从而将多样性转化为显式优化信号。我们的框架具备即插即用和模型无关的特性，能在保持提示忠实度与感知质量的同时，显著提升视频在视觉外观、摄像机运动和场景结构等方面的多样性。我们在WAN和CogVideoX模型上实现该方法，实验表明其在VBench、VideoScore等前沿基准测试及人类偏好研究中持续提升视频多样性。此外，我们开源了代码并发布包含3万条多样化提示的新基准数据集，以支持后续研究。

English

While recent text-to-video (T2V) diffusion models have achieved impressive quality and prompt alignment, they often produce low-diversity outputs when sampling multiple videos from a single text prompt. We tackle this challenge by formulating it as a set-level policy optimization problem, with the goal of training a policy that can cover the diverse range of plausible outcomes for a given prompt. To address this, we introduce DPP-GRPO, a novel framework for diverse video generation that combines Determinantal Point Processes (DPPs) and Group Relative Policy Optimization (GRPO) theories to enforce explicit reward on diverse generations. Our objective turns diversity into an explicit signal by imposing diminishing returns on redundant samples (via DPP) while supplies groupwise feedback over candidate sets (via GRPO). Our framework is plug-and-play and model-agnostic, and encourages diverse generations across visual appearance, camera motions, and scene structure without sacrificing prompt fidelity or perceptual quality. We implement our method on WAN and CogVideoX, and show that our method consistently improves video diversity on state-of-the-art benchmarks such as VBench, VideoScore, and human preference studies. Moreover, we release our code and a new benchmark dataset of 30,000 diverse prompts to support future research.

基于行列式点过程引导策略优化的多样化视频生成

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization

摘要

Support