facebookresearch / sam-3d-bodyView external linksLinks
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.
☆2,595Dec 19, 2025Updated last month
Alternatives and similar repositories for sam-3d-body
Users that are interested in sam-3d-body are comparing it to the libraries listed below
Sorting:
- SAM 3D Objects☆5,953Feb 3, 2026Updated last week
- Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body…☆575Feb 7, 2026Updated last week
- 🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.☆238Updated this week
- The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading t…☆7,665Feb 3, 2026Updated last week
- [NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation☆416May 22, 2025Updated 8 months ago
- HumEnv is an SMPL humanoid environment enabling systematic model comparison and reproducibility☆116Apr 22, 2025Updated 9 months ago
- A library for human kinematic motion and numerical optimization solvers to apply human motion☆291Updated this week
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆12,448Oct 11, 2025Updated 4 months ago
- ☆991Apr 18, 2024Updated last year
- [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy☆909Sep 26, 2025Updated 4 months ago
- Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024☆1,379Jul 14, 2025Updated 7 months ago
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆2,885Jan 18, 2026Updated 3 weeks ago
- The Fast Way From Vertices to Parametric 3D Humans☆164Feb 6, 2026Updated last week
- ☆270Jan 14, 2026Updated last month
- An unified model for 4D human-scene reconstruction☆440Dec 30, 2025Updated last month
- Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"☆1,225Jan 5, 2026Updated last month
- [ICCV 2025 Highlight] VolumetricSMPL☆84Jul 27, 2025Updated 6 months ago
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆1,630Jan 28, 2026Updated 2 weeks ago
- TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos☆586Jun 8, 2025Updated 8 months ago
- Depth Anything 3☆4,359Dec 12, 2025Updated 2 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,287Nov 2, 2025Updated 3 months ago
- Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral☆42Jan 16, 2026Updated last month
- [CVPR 2025 Highlight] SkillMimic: Learning Basketball Interaction Skills from Demonstrations☆400Jun 30, 2025Updated 7 months ago
- [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"☆395Sep 19, 2025Updated 4 months ago
- [CVPR 2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”☆383Sep 14, 2025Updated 5 months ago
- Cameras as Relative Positional Encoding☆677Dec 18, 2025Updated last month
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,336Aug 27, 2025Updated 5 months ago
- A Modular Framework for 3D Gaussian Splatting and Beyond☆1,709Nov 5, 2025Updated 3 months ago
- ViPE: Video Pose Engine for Geometric 3D Perception☆1,717Jan 1, 2026Updated last month
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆1,756Oct 7, 2025Updated 4 months ago
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,334Jun 16, 2025Updated 7 months ago
- Reference PyTorch implementation and models for DINOv3☆9,590Nov 20, 2025Updated 2 months ago
- 4DHumans: Reconstructing and Tracking Humans with Transformers☆1,540Feb 7, 2026Updated last week
- [CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"☆776Aug 26, 2024Updated last year
- [CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation☆337Oct 3, 2025Updated 4 months ago
- SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆497Updated this week
- DUSt3R: Geometric 3D Vision Made Easy☆6,950Sep 24, 2025Updated 4 months ago
- [CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration☆1,196Sep 17, 2024Updated last year
- [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.☆514Apr 1, 2025Updated 10 months ago