Meta's SAM 3 and DINOv3 Power Automated Segmentation Pipeline at DOE National Labs

Meta's open-source models SAM 3 and DINOv3 are powering the SYNAPS-I pipeline at DOE national labs including Lawrence Berkeley, Argonne, Brookhaven, and Oak Ridge. The pipeline automates scientific image segmentation — work that previously consumed weeks of expert effort per dataset — at facilities whose upgraded detectors now capture 100,000 images per second, producing tens of petabytes annually.