Physicl launches Studio and announces seed round funding
Understand this story
Physicl has launched Studio, a synthetic training data tool, and simultaneously announced the completion of a seed round of funding. Users describe in natural language the scenarios in which a model fails, and Studio matches scenarios from a library of 10,000 environments and 100,000 assets, suggests dimensions of variation, and renders images and videos with per-frame ground truth, including depth, surface normals, segmentation, boxes, and camera poses. Studio is currently in beta, released in batches to research teams building vision, world models, and robotics models, and is free during the beta period. Physicl said research teams will receive access in batches, and that free access is limited to the beta period.
AI overview based on source reports · Updated 1 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIPhysical AI can't learn from the internet. We build the worlds it learns from
Physicl launched Studio, a beta app that lets researchers describe a failure case in plain words and then proposes a matching scene from a library of 10,000 environments and 100,000 assets, suggesting variations to cover it. It renders images and video with ground truth computed from the 3D scene on every frame, including depth, surface normals, segmentation, boxes and camera pose. Studio is free during the beta and opening to research teams in waves.
Activity for this story
Not enough continuous observations to show a trend yet.