Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
This addresses a critical challenge in personalized video generation for applications like entertainment or virtual reality, though it is incremental as it refines existing methods.
The paper tackled the problem of preserving consistent identities for multiple humans in generated videos, achieving up to 18.9% improvement in human consistency metrics over baseline methods.
While advanced methods like VACE and Phantom have advanced video generation for specific subjects in diverse scenarios, they struggle with multi-human identity preservation in dynamic interactions, where consistent identities across multiple characters are critical. To address this, we propose Identity-GRPO, a human feedback-driven optimization pipeline for refining multi-human identity-preserving video generation. First, we construct a video reward model trained on a large-scale preference dataset containing human-annotated and synthetic distortion data, with pairwise annotations focused on maintaining human consistency throughout the video. We then employ a GRPO variant tailored for multi-human consistency, which greatly enhances both VACE and Phantom. Through extensive ablation studies, we evaluate the impact of annotation quality and design choices on policy optimization. Experiments show that Identity-GRPO achieves up to 18.9% improvement in human consistency metrics over baseline methods, offering actionable insights for aligning reinforcement learning with personalized video generation.