BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation
This addresses the limited research in customized text-to-video generation for storytelling content creation, representing an incremental advancement.
The paper tackled the problem of poor generalization and information loss in customized text-to-video generation by proposing an autoregressive structure and texture propagation module and a test-time reward optimization method, resulting in improvements of 7.8 and 13.1 in CLIP-I and DINO consistency metrics over the baseline.
Both zero-shot and tuning-based customized text-to-image (CT2I) generation have made significant progress for storytelling content creation. In contrast, research on customized text-to-video (CT2V) generation remains relatively limited. Existing zero-shot CT2V methods suffer from poor generalization, while another line of work directly combining tuning-based T2I models with temporal motion modules often leads to the loss of structural and texture information. To bridge this gap, we propose an autoregressive structure and texture propagation module (STPM), which extracts key structural and texture features from the reference subject and injects them autoregressively into each video frame to enhance consistency. Additionally, we introduce a test-time reward optimization (TTRO) method to further refine fine-grained details. Quantitative and qualitative experiments validate the effectiveness of STPM and TTRO, demonstrating improvements of 7.8 and 13.1 in CLIP-I and DINO consistency metrics over the baseline, respectively.