5 papers
Mind the RefGAP: Correcting Reference Attention in Diffusion-Based Visual Editing
Yanan Wang, Shengcai Liao, Guangyi Liu +1
Reference-guided diffusion editors struggle to faithfully reproduce user-provided references. We identify a potential bottleneck in diffusion editors: many methods provide limited…
DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation
Yanan Wang, Shengcai Liao, Panwen Hu +4
Head swapping replaces an entire head while preserving pose, expression, body motion, and scene. Progress is limited by the lack of cross-identity paired videos: real footage canno…
BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation
Panwen Hu, Jiehui Huang, Qiang Sun +1
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 tex…
StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
Panwen Hu, Jin Jiang, Jianqi Chen +4
The advent of AI-Generated Content (AIGC) has spurred research into automated video generation to streamline conventional processes. However, automating storytelling video producti…
Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models
Sanoojan Baliah, Qinliang Lin, Shengcai Liao +2
Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color…