BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation

TL;DR

This paper introduces BridgeIV, a novel method for customized text-to-video generation that uses autoregressive feature propagation and test-time optimization to improve structural and texture consistency, outperforming existing methods.

Contribution

The paper presents a new autoregressive structure and texture propagation module combined with test-time reward optimization for enhanced customized text-to-video generation.

Findings

Improved CLIP-I consistency by 7.8 points.

Enhanced DINO consistency by 13.1 points.

Validated effectiveness through extensive experiments.

Abstract

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.