SOMA reconstructs subsurface muscle deformation from plain RGB video
danbri · x · 2026-09-06
SOMA is an AI system that recovers muscle deformation beneath the skin from ordinary RGB camera video:
- Observes skin surface and pose from video to estimate muscle deformation directly
- Generates multi-layer human body models covering skin, muscle, and bone
- Training data (SKIM) was built with 120 cameras plus a special marker suit
The key point: it skips FEM simulation entirely, producing anatomically plausible human animation from surface observation alone — relevant for character animation, avatars, and movement science.
More from Research
- Five-Year Retrospective Argues ML-Assisted Directed Evolution Ignores Real-World Costs — anshulkundaje · 2026-09-06
- Google maps full fruit fly brain with AI, reconstructing 166,000+ neurons in 3D — zacharynado · 2026-09-06
- Skip SFT, run GRPO on a 0.8B Qwen base model and watch reasoning emerge — alexcovo_eth · 2026-09-06
- Mathematician littmath: the community should reward AI 'last-mile' work less — littmath · 2026-09-06
- MirroS' Code-as-World Beats Gemini-3.1 Flash on Physical Reasoning Benchmark — jiqizhixin · 2026-09-06
- HF's Merve shares Blender+GRPO training rollouts and VLM-judge debugging pitfalls — mervenoyann · 2026-09-06