8 papers · 1 filter
4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
Renlong Wu, Haoran Chen, Yuxiang Wei +3
Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view videos first and then fit a 4D…
Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle
Weidong Qiao, Wangmeng Zuo, Hui Li
Modeling 4D scenes requires capturing both spatial structure and temporal motion, which is challenging due to the need for physically consistent representations of complex rigid an…
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
Haoze Zhang, Tianyu Huang, Zichen Wan +4
While recent video generation models have achieved significant visual fidelity, they often suffer from the lack of explicit physical controllability and plausibility. To address th…
PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
Yu Yang, Zhilu Zhang, Xiang Zhang +3
Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models…
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
Tianyu Huang, Wangguandong Zheng, Tengfei Wang +8
Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant…
Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splatting
Feng Yang, Wenliang Qian, Wangmeng Zuo +1
Score Distillation Sampling (SDS) leverages pretrained 2D diffusion models to advance text-to-3D generation but neglects multi-view correlations, being prone to geometric inconsist…