The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Code release for NeRF (Neural Radiance Fields)

Best Practices, code samples, and documentation for Computer Vision.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…

[ICCV 2019] Monocular depth estimation from a single image

A simplified implemention of Faster R-CNN that replicate performance from origin paper

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

Metric depth estimation from a single image

Chess reinforcement learning by AlphaGo Zero methods.

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Try out deep learning models online on Google Colab

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

High Quality Monocular Depth Estimation via Transfer Learning

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Tracking Any Point (TAP)

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

A Modular Framework for 3D Gaussian Splatting and Beyond

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

VPoser: Variational Human Pose Prior

Keras version of Realtime Multi-Person Pose Estimation project

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

Light-weight Single Person Pose Estimator

Data preparation and loader for AMASS

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN