paper-with-me

홈 › Papers

Discriminator-Free Direct Preference Optimization for Video Diffusion

2025-04-11 · Haoran Cheng, Qide Dong, Liang Peng, Zhizhou Sha, Weiguo Feng, Jinghui Xie, Zhao Song, Shilei Wen, Xiaofei He, Boxi Wu

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical challenges: (1) Data inefficiency. Generating thousands of videos per DPO iteration incurs prohibitive costs; (2) Evaluation uncertainty. Human annotations suffer from subjective bias, and automated discriminators fail to detect subtle temporal artifacts like flickering or motion incoherence. To address these, we propose a discriminator-free video DPO framework that: (1) Uses original real videos as win cases and their edited versions (e.g., reversed, shuffled, or noise-corrupted clips) as lose cases; (2) Trains video diffusion models to distinguish and avoid artifacts introduced by editing. This approach eliminates the need for costly synthetic video comparisons, provides unambiguous quality signals, and enables unlimited training data expansion through simple editing operations. We theoretically prove the framework's effectiveness even when real videos and model-generated videos follow different distributions. Experiments on CogVideoX demonstrate the efficiency of the proposed method.

📄 PDF Abstract BibTeX arXiv:2504.08542

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
DPO 설명 없음

Similar Papers 제목 키워드 기반

Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation

2025-11-03 · Jie Du, Xinyu Gong, Qingshan Tan, Wen Li 외 arxiv

Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largely follow image-domain paradigms and are …

Video Generation

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

2024-12-19 · Yatai Ji, Jiacheng Zhang, Jie Wu, Shilong Zhang 외

Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the …

Video Generation

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

2025-03-03 · Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He 외

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the f…

Image Generation

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

2026-06-17 · Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng, Reyhane Askari-Hemmat 외 arxiv

Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent ob…

Reinforcement Learning

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning

2026-01-07 · Yifan Wang, Yanyu Li, Gordon Guocheng Qian, Sergey Tulyakov 외 arxiv

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Mo…