6 papers
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
Hongyu Li, Wanjia Fu, Xiaoyan Cong +11
Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to…
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
Hongyang Du, Junjie Ye, Xiaoyan Cong +7
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deforma…
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
Zekun Li, Sizhe An, Chengcheng Tang +7
Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language ge…
GenHSI: Controllable Generation of Human-Scene Interaction Videos
Zekun Li, Rui Zhou, Rahul Sajnani +3
Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in generating…
Art3D: Training-Free 3D Generation from Flat-Colored Illustration
Xiaoyan Cong, Jiayi Shen, Zekun Li +3
Large-scale pre-trained image-to-3D generative models have exhibited remarkable capabilities in diverse shape generations. However, most of them struggle to synthesize plausible 3D…
PackUV: Packed Gaussian UV Maps for 4D Volumetric Video
Aashish Rai, Angela Xing, Anushka Agarwal +5
Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality re…