5 papers
ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning
Bangya Liu, Xinyu Gong, Zelin Zhao +6
Human-object interaction (HOI) video generation has garnered increasing attention due to its promising applications in digital humans, e-commerce, advertising, and robotics imitati…
Bidirectional Sparse Attention for Faster Video Diffusion Training
Chenlu Zhan, Wen Li, Chuyu Shen +3
Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic com…
CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization
Zelin Zhao, Xinyu Gong, Bangya Liu +5
Achieving precise camera control in video generation remains challenging, as existing methods often rely on camera pose annotations that are difficult to scale to large and dynamic…
Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
Jie Du, Xinyu Gong, Qingshan Tan +7
Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largel…
DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
Weitao Wang, Zichen Wang, Hongdeng Shen +6
With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevaili…