7 papers
GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction
Zhenlong Wu, Zihan Zheng, Xuanxuan Wang +7
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts i…
ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention
Huiguo He, Pengyu Yan, Ziqi Yi +6
Drag-based image editing enables intuitive visual manipulation through point-based drag operations. Existing methods mainly rely on diffusion inversion or pixel-space warping with…
DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion
Huiguo He, Huan Yang, Zixi Tuo +7
Story visualization aims to create visually compelling images or videos corresponding to textual narratives. Despite recent advances in diffusion models yielding promising results,…
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation
Xin Yan, Yuxuan Cai, Qiuyue Wang +3
We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain…
Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention
Huiguo He, Qiuyue Wang, Yuan Zhou +4
Training-free diffusion models have achieved remarkable progress in generating multi-subject consistent images within open-domain scenarios. The key idea of these methods is to inc…
Fleximo: Towards Flexible Text-to-Human Motion Video Generation
Yuhang Zhang, Yuan Zhou, Zeyu Liu +4
Current methods for generating human motion videos rely on extracting pose sequences from reference videos, which restricts flexibility and control. Additionally, due to the limita…