Meta says SAM 3 and DINOv3 cut a lab imaging workflow from one month to 15 minutes
imjustnewatai · x · 2026-07-23
Meta says SAM 3 and DINOv3 can drastically cut annotation work on a Berkeley Lab imaging task.
- A month of manual annotation was reduced to 15 minutes.
- Running across 300 A100s, the system reconstructs and labels 3D volumes while experiments are still in progress.
- The post highlights a practical lab workflow where vision models help turn raw imaging into usable annotations much earlier in the process.
Related event: Meta's SAM 3 and DINOv3 Reduce Imaging Annotation to 15 Minutes(2 posts)→
More from Multimodal
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- FastH3-Live hits 22fps: acceleration node benchmarks and the --vram-headroom trick — spartong945 · 2026-09-11
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11