Meta open-sources SAM 3 and DINOv3 for Genesis Mission: scientific image analysis in 15 minutes

On July 21, 2026, Meta released two computer vision models, Segment Anything Model 3 (SAM 3) and DINOv3, as open source for the US Genesis Mission, a federal science initiative. Together, they cut the analysis of scientific images from months of manual work to about 15 minutes.

What is the Genesis Mission

The Genesis Mission is a White House initiative, launched by the US Department of Energy (DOE) in late 2025, to accelerate scientific discovery with AI. Its flagship project, SYNAPS-I (SYnergistic Neutron And Photon Science – Intelligence), brings together five national laboratories and turns the processing of data from scientific instruments from a bottleneck measured in months into near-real-time analysis.

Key participants and figures:

• Five DOE laboratories: Berkeley Lab, Argonne, Brookhaven, Oak Ridge and SLAC
• About 60 researchers on the SYNAPS-I team
• Two open Meta models: SAM 3 and DINOv3
• The fine-tuned pipeline runs on 300 NVIDIA A100 GPUs at the NERSC computing center
• Result: a labeled 3D volume in about 15 minutes

How SAM 3 and DINOv3 work

The two models split the work: DINOv3 finds structures in an image, and SAM 3 outlines them with pixel-level precision. DINOv3 is a self-supervised vision model, meaning it learns to recognize visual patterns without manual labeling by humans. SAM 3 traces object boundaries as carefully as a scientific annotator working by hand, but does it in seconds rather than hours.

The joint pipeline was fine-tuned on scientific images and run on 300 A100 GPUs at NERSC. According to the Meta AI blog, the system produces fully reconstructed, semantically labeled three-dimensional volumes in about 15 minutes.

Where it has already been applied

The first test was an analysis of drought tolerance in grapevines using micro-CT images. The pipeline builds a 3D model of the vine stem and automatically finds the xylem vessels, the tubes that carry water. Previously, this labeling took about a month per time step; now the plant's response to drought can be studied in near real time.

The scale of the data explains why this matters. Berkeley Lab operates the Advanced Light Source (ALS), a synchrotron light source: after its upgrade, it produces tens of petabytes of data a year, equivalent to 2 million hours of HD video, and its detectors capture up to 100,000 images per second. That flow cannot be sorted by hand.

"Artificial intelligence, advanced computing and experimental systems

now analyze data as it is generated and steer experiments in real time, replacing slow manual steps with adaptive, automated decision-making," said Dario Gil, US Under Secretary of Energy.

Why open models matter

The open license allows the national laboratories to download the models, fine-tune them and deploy them inside secure government infrastructure, without relying on external clouds. For science, this is critical: data from unpublished research stays under the control of all five SYNAPS-I laboratories until publication.

What this means

General-purpose AI models from industry are moving into fundamental science: work that used to hold up discoveries for months now takes minutes. Open access to SAM 3 and DINOv3 gives government labs a world-class tool that they can keep on their own servers.

Frequently asked questions

Which Meta models are used in the Genesis Mission?

Two open computer vision models: Segment Anything Model 3 (SAM 3) and DINOv3. DINOv3 finds structures in an image, and SAM 3 outlines their boundaries with pixel-level precision.

Are SAM 3 and DINOv3 free?

Yes, Meta has released both models as open source. They can be downloaded, fine-tuned on your own data and deployed inside secure infrastructure without external cloud services.

How much faster is the data analysis?

Labeling xylem vessels in grapevine images used to take about a month per time step. The new pipeline, running on 300 A100 GPUs at NERSC, produces a finished 3D volume in about 15 minutes.

*Meta has been designated an extremist organization and is banned in Russia.