nvidia-cosmos / cosmos-predict1
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
☆99Updated this week
Alternatives and similar repositories for cosmos-predict1:
Users that are interested in cosmos-predict1 are comparing it to the libraries listed below
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆290Updated this week
- ☆122Updated 2 months ago
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆98Updated 4 months ago
- [ICLR 2025] Official Implementation of M3: 3D-Spatial Multimodal Memory☆118Updated last week
- PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos☆80Updated this week
- ☆85Updated 3 weeks ago
- [CVPR 2024] Official code for EgoGen: An Egocentric Synthetic Data Generator☆78Updated 3 weeks ago
- A Video Tokenizer Evaluation Dataset☆109Updated 2 months ago
- Code for FlowCam☆146Updated last year
- Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025)☆156Updated 3 months ago
- Independent PyTorch Implementation of Object Scene Representation Transformer☆48Updated last year
- [CVPR 2024] Official repository for "Tactile-Augmented Radiance Fields".☆55Updated last month
- HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos☆47Updated 3 weeks ago
- Aether: Geometric-Aware Unified World Modeling☆120Updated last week
- ☆130Updated 3 months ago
- MEt3R: Measuring Multi-View Consistency in Generated Images☆92Updated 3 weeks ago
- [ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts☆194Updated 4 months ago
- ☆98Updated 8 months ago
- Official JAX Implementation of Monocular Dynamic View Synthesis: A Reality Check (NeurIPS 2022)☆192Updated 3 months ago
- Agent-to-Sim Learning Interactive Behavior from Casual Videos.☆42Updated 5 months ago
- Code for "Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling" (CoRL 2024)☆97Updated 3 months ago
- Code for Few-View Object Reconstruction with Unknown Categories and Camera Poses at 3DV 2024 (oral)☆89Updated last year
- Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data☆147Updated 5 months ago
- Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".☆85Updated last week
- ☆80Updated 3 weeks ago
- Generative World Explorer☆138Updated 4 months ago
- Official PyTorch Implementation of "History-Guided Video Diffusion"☆241Updated 3 weeks ago
- ☆63Updated last year
- Stereo4D dataset and processing code☆132Updated this week
- Feature splatting based on INRIA GS rasterizer☆73Updated 2 weeks ago