An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

Fast Segment Anything

Reference implementation of Mistral AI 7B v0.1 model.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Pipeline Parallelism for PyTorch

An experimental open-source attempt to make GPT-4 fully autonomous.

Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

This repository contains texture stitching code corresponding to the paper Detailed Human Avatars from Monocular Video.

Jetson Nano ML install scripts, automated optimization of robotics detection models, and filter-based tracking of detections

Implementation of ECCV'18 paper - GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints

Code for GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Exploiting temporal information for 3D pose estimation