OpenAI: AI agents build 3D scenes from photos but have no idea if they got it right
In shortThe Decoder reports that a new approach called LEGO-Anything turns single photos into editable Blender code for 3D scenes; GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy.
Based on reporting from The Decoder; no matching primary source is listed in the Source Stack yet.
What happened
The Decoder reports that GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy.
What the report says
- The Decoder reports that a new approach called LEGO-Anything turns single photos into editable Blender code for 3D scenes; GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy.
Who it affects
Software developers and engineering teams · Developers and product teams · Researchers and evaluation teams
Following the story
What happened after the announcement
Newly verified: The Decoder reports that GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy.
Still watching: Has comparable external evidence confirmed, limited or contradicted the result in “OpenAI: AI agents build 3D scenes from photos but have no idea if they got it right”?
This fresh brief is based on concrete independent reporting; a matching official statement is not yet available.