GPT-6 Astra builds 3D scenes from video, augmented with SAM3, Pi3X and Blender sim
yshan2u · x · 2026-09-28
Siyuan Bian demonstrates that GPT-6's Astra can build 3D scenes from video, but notes gaps in accuracy, physical plausibility, and interactivity.
The team's approach: integrate 3D vision tools into Astra's agentic workflow — Pi3X, SAM3, GVHMR/Kimodo for human motion capture, and Blender simulation — to make generated scenes more physically grounded and richly interactive. A demo video is linked.
Related event: GPT-6 Astra Turns Real Video into 3D Worlds for Robot Training(2 posts)→
More from coding & agent
- Baseten's Guide: Evaluate Open Models for Coding Agents on Your Own PRs — baseten · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16