NVlabs/FoundationPose

[CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

End-to-End Object Detection with Transformers

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[DEIMv2] Real Time Object Detection Meets DINOv3

[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning