Alibaba Group (Tongyi Lab) · 3D Reconstruction
LHM - Large Animatable Human Reconstruction Model
LHM reconstructs high-fidelity, animatable 3D human avatars from single images in seconds using 3D Gaussian splatting and a multimodal transformer architecture. The model preserves detailed clothing geometry, facial identity, and hand details without post-processing through a novel head feature pyramid encoding scheme.
Open the source ↗Similar 3D & Spatial releases
- Idol
Speridlabs (Alejandro Cañada, Chema Garabito) · Image-to-3D splats · Week 45, 2026
- JST-2
Viggle AI · World Model · Week 44, 2026
- InfiniSplat v2
Zhejiang University, Shenzhen University, Hello TransTech and Causa Robotics · Feed-Forward Gaussian Splatting · Week 43, 2026
- GaussiAnimate
Westlake University, Nanjing University, HKU and MUST · 4D Rigging · Week 43, 2026
- FixAnything
Carnegie Mellon University · Rendering Refinement · Week 35, 2026
- SplatKit
mickmumpitz · Gaussian Splatting · Week 35, 2026
More from Alibaba Group (Tongyi Lab)
- OmniTalker
Alibaba Group (Tongyi Lab) · Text-to-Video · Week 14, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.