yangtiming/Fast-SAM-3D-Body: [ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery ·
github.com · 604 words · saved by 1 readers
[ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
[ECCV 2026] Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery Timing Yang1, Sicheng He1, Hongyi Jing1, Jiawei Yang1, Zhijian Liu2,3, Chuhang Zou4†, Yue Wang1,3† 1USC Physical Superintelligence (PSI) Lab 2University of California, San Diego 3NVIDIA 4Meta Reality Labs † Joint corresponding authors Speed-accuracy overview of Fast SAM 3D Body. Top left: Qualitative results on in-the-wild images show our framework preserves high-fidelity reconstruction. Top right: Our method achieves up to a 10.25x end-to-end speedup over SAM 3D Body and replaces the iterative MHR-to-SMPL…
saved by
related reading
- GitHub - AmmarkoV/SAM3DBody-cpp: Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.github.com
- GitHub - cuevhv/mamma: Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.github.com
- Kimodo: Scaling Controllable Human Motion Generationresearch.nvidia.com
- Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusionarxiv.org
- Learning Sim-to-Real Humanoid Locomotion in 15 Minutesyounggyo.me
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation | PDFarxiv.org
- S4Darxiv.org
- Differentiable Robot Renderingdrrobot.cs.columbia.edu
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- Helix: A Vision-Language-Action Model for Generalist Humanoid Controlfigure.ai
- Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wildlift4d.github.io
- RTFM: A Real-Time Frame Model | World Labsworldlabs.ai