MultimodalSensor / Time-seriesVideo
Open X-Embodiment
1M+ real-robot trajectories from 20+ institutions.
1M–10M·Apache-2.0·rosbag
3D / Point CloudImageMultimodalVideo
DiffusionGS
ICCV 2025 DiffusionGS: Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction…
ICCV 2025 DiffusionGS: Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction Data Description These are the demo results of our ICCV 2025 paper. HuggingFace Model Link We also release our models in HuggingFace: Here are some video generation results demo: · (a) Object-level Generation… See the full description on the dataset page:
Source: Hugging Face Hub (CaiYuanhao/DiffusionGS). Metadata imported from the dataset’s Hub tags.