Owner

facebookresearch

217 indexed repositories · View on GitHub

• faiss

  A library for efficient similarity search and clustering of dense vectors.

  C++ · 40909 stars

• detectron2

  Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

  Python · 34707 stars

• audiocraft

  Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor...

  Jupyter Notebook · 23627 stars

• sam2

  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode...

  Jupyter Notebook · 19859 stars

• vggt

  [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

  Python · 14390 stars

• dinov2

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

  Jupyter Notebook · 13330 stars

• seamless_communication

  Foundational Models for State-of-the-Art Speech and Text Translation

  Jupyter Notebook · 11855 stars

• sam3

  The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading t...

  Python · 11672 stars

• dinov3

  Reference PyTorch implementation and models for DINOv3

  Jupyter Notebook · 11384 stars

• xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Python · 10547 stars

• pytorch3d

  PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

  Python · 9968 stars

• ImageBind

  ImageBind One Embedding Space to Bind Them All

  Python · 9072 stars

• SlowFast

  PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

  Python · 7421 stars

• sam-3d-objects

  SAM 3D Objects

  Python · 7396 stars

• Kats

  Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analy...

  Python · 6470 stars

• mmf

  A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

  Python · 5632 stars

• sapiens

  High-resolution models for human tasks.

  Python · 5423 stars

• moco

  PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

  5135 stars

• co-tracker

  CoTracker is a model for tracking any point (pixel) on a video.

  Jupyter Notebook · 5104 stars

• AugLy

  A data augmentations library for audio, image, text, and video.

  Python · 5097 stars

• 197 more repositories live on View on GitHub