Meta says SAM 3 and DINOv3 cut 3D volume labeling from a month to 15 minutes
AIatMeta · x · 2026-07-22
Meta says the Berkeley Lab-led SYNAPS-I project is using SAM 3 and DINOv3 to automate image segmentation for scientific discovery.
- The two models are paired to combine global semantic context (DINOv3) with pixel-level boundary extraction (SAM 3).
- Researchers say this reduces 3D volume labeling from about a month of manual work to roughly 15 minutes.
- Meta frames the effort as support for DOE’s Genesis Mission and real-time scientific analysis.
Related event: Meta's SAM 3 and DINOv3 Reduce Imaging Annotation to 15 Minutes(2 posts)→
More from Research
- AI folks, stop saying "biology" when you mean drug development — KevinKaichuang · 2026-10-26
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26
- Shanghai AI Lab-led team releases 100-hour egocentric wearable dataset for humanoid training — ChuckDBrooks · 2026-10-26
- Flow Reasoning Models turn flow matching into iterative reasoners, hitting 99.5% on Sudoku-Extreme — alec_helbling · 2026-10-26
- Surprising find: Alzheimer's-linked amyloid fibrils deliver RNA to sperm for embryo translation — EricTopol · 2026-10-26
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26