Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

The best ChatGPT that $100 can buy.

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

A library for human kinematic motion and numerical optimization solvers to apply human motion

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…

This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

3D Object Reconstruction project is a workflow that takes a set of stereo images and camera info and outputs a textured mesh (i.e., .OBJ file). The purpose is to translate physical items into the d…

Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

GoTrack: Generic 6DoF Object Pose Refinement and Tracking, CV4MR 2025

Minimal solvers for calibrated camera pose estimation

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

[ICLR 2025] 6D Object Pose Tracking in Internet Videos for Robotic Manipulation

Benchmarks for Industrial Bin-Picking Pose Estimation on BOP Challenge 2025

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

Codebase for Perception Challenge For Bin-Picking

Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.

[ICCV 2023] Deep Active Contours for Real-time 6-DoF Object Tracking

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

FoundPose: Unseen Object Pose Estimation with Foundation Features, ECCV 2024

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)

EgoBody3M Egocentric Body Tracking on a VR Headset using a Diverse Dataset

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos, CVPR 2025

Toolkit to download/upload datasets for BOP benchmark

Visualization kit for BOP benchmark