Back to the work
Computer Vision · Explorer

Recognize (SAM3 Experiments).

Short experiments running Meta's SAM3 (Segment Anything Model 3) on images with text prompts, plus a small script to visualize the predicted masks.

PythonPyTorchSAM3PIL
Role ExplorerPeriod 2026Domain Computer Vision
§ 01The problem.

Try Meta's SAM3 for promptable, open-vocabulary segmentation: point it at an image, give it a text prompt, and see what it can segment, as a hands-on way to understand the model rather than a product.

§ 02How it works.
  1. Pulls in Meta's SAM3 as a git submodule and uses its model builder and image processor directly, no reimplementation.
  2. A short run script builds the SAM3 image model, sets an image, applies a text prompt (for example 'person'), and reads back masks, boxes, and confidence scores.
  3. A companion script visualizes the predicted masks over the image.
§ 03Results and impact.
  • A small, working reference for promptable segmentation with SAM3: prompt an image and get masks, boxes, and scores in a few lines.
  • Exploratory by design, this is a learning experiment with Meta's model, not an original system.