facebookresearch

facebookresearch

fairseq2

★ 1,154

FAIR Sequence Modeling Toolkit 2

facebookresearch

CutLER

★ 1,079

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

facebookresearch

sapiens2

★ 1,038

1K resolution vision transformers pretrained on 1B human images.

facebookresearch

ProgramBench

★ 978

Can Language Models Rebuild Programs From Scratch?

facebookresearch

mobile-vision

★ 923

Mobile vision models and code

facebookresearch

cwm

★ 919

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

facebookresearch

MHR

★ 906

Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

facebookresearch

ShapeR

★ 902

Code for the ShapeR research paper

facebookresearch

projectaria_tools

★ 868

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data.

facebookresearch

context-language-models

★ 867

Official repository for "Context Language Models"

facebookresearch

project_superdex

★ 833

SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.

facebookresearch

videoseal

★ 822

Open and efficient video and image watermarking

facebookresearch

eb_jepa

★ 813

An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.

facebookresearch

audioseal

★ 803

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

facebookresearch

ocean

★ 799

Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.

facebookresearch

balance

★ 779

The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.

facebookresearch

tuna-2

★ 763

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

facebookresearch

EUPE

★ 737

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

facebookresearch

silk

★ 684

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

facebookresearch

boxer

★ 680

Code for the Boxer research paper