The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Kolmogorov Arnold Networks

PyTorch code and models for the DINOv2 self-supervised learning method.

Reference PyTorch implementation and models for DINOv3

GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse m…

The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating

BotanicGarden: A high-quality dataset for robot navigation in unstructured natural environments

[ICCV 2025] SAM4D: Segment Anything in Camera and LiDAR Streams

BoQ: A Place is Worth a Bag of learnable Queries (CVPR 2024)

Code release for Revisit Anything: Visual Place Recognition via Image Segment Retrieval (ECCV 2024)

The GrandTour Dataset: A Legged Robotics Dataset in the Wild

Place Recognition library based on Python and PyTorch framework

Learn symforce together :)

ELSED: Enhanced Line SEgment Drawing