You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
facebookresearch/ads_model_kernel_library’s past year of commit activity
High-performance GPU kernels for Ads and Recsys model training, independently implemented and optimized for real-world workloads and model-specific input charac…
This repository contains code to generate and preprocess Learning with Errors (LWE) data and implementations of four LWE attacks uSVP, SALSA, Cool&Cruel, and Du…
facebookresearch/ocean’s past year of commit activity
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 i…
VRS is a file format optimized to record & playback streams of sensor data, such as images, audio samples, and any other discrete sensors (IMU, temperature, etc…
facebookresearch/Online-3DGS-Monocular’s past year of commit activity
Code repo for the SIGGRAPH paper "Monocular Online Reconstruction with Enhanced Detail Preservation". Project page https//poiw.github.io/MODP/index.html
Efficient image to 3D geometry foundation models from Meta Reality Labs for monocular depth, point maps, and surface normals. Featuring HyDen (ICLR 2026).
The Visual Environment Evaluation Tool (VEET) device is a pair of temple arm form-factor devices that allow a researcher to gather visual information that the e…
Reading speed, image quality ratings, and comfort ratings in augmented reality, a benchmark dataset of 11,600+ measurements across 84 display conditions from 10…
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkp…
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 o…
Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.gith…