FlowHMR gets 5x faster, demoing an LLM agent pipeline from video to photoreal mocap
camenduru · x · 2026-11-02
FlowHMR (monocular human mocap) reports a major speedup: 5× faster end-to-end processing on 300-frame videos with a static camera. The model is live on Hugging Face with open code.
The team also demoed a full agent-driven mocap pipeline:
- An LLM agent parses "create a simple 3D animation from this video", builds the scene, and calls FlowHMR for motion capture;
- The agent then handles retargeting, motion fixes, camera setup and rendering;
- MiniMax-H3 finally turns the 3D render into a photorealistic video.
More from coding & agent
- DeepSeek design doc: a person can only follow 3-5 agent sessions at once, attention is the real bottleneck — heyshrutimishra · 2026-11-02
- Software fundamentals are key to getting good results from AI coding agents — bendee983 · 2026-11-02
- Open-source LLM regression gate digline hits 1.0: quantifying judge noise before calling a regression — alexpran · 2026-11-02
- PR adds patient retry logic for model capacity errors in OpenAI Codex — bytebot · 2026-11-02
- Perplexity open-sources WANDR: 500 research tasks, 170,495 evidence points, URL-rechecking grader — thisguyknowsai · 2026-11-02
- 4 AIs, 96 questions, 2,671 citations: 74% are blog posts, 99% on companies' own sites — tibo_maker · 2026-11-02