ModelScope: bring the notion of Model-as-a-Service to life.

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

Official Code for DragGAN (SIGGRAPH 2023)

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.

A platform for building proxies to bypass network restrictions.

⭐ Linux / Windows / macOS 跨平台 V2Ray 客户端 | 支持 VMess / VLESS / SSR / Trojan / Trojan-Go / NaiveProxy / HTTP / HTTPS / SOCKS5 | 使用 C++ / Qt 开发 | 可拓展插件式设计 ⭐

Convolutional Neural Networks

Piccolo (formerly Pilot) – mini game engine for games104

Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.

Pytorch framework for doing deep learning on point clouds.

BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

Windows system utilities to maximize productivity

myCobot is the World's Smallest Collaborative Robot Arm.

EgocentricReconstruction

Aria data tools provide the open-source toolkit in C++ and Python to interact with data from Project Aria (https//about.facebook.com/realitylabs/projectaria/)

PixelNeRF Official Repository

[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

Neural Unsigned Distance Fields (NDF) - Codebase

Code release of paper Improving neural implicit surfaces geometry with patch warping

improves over nerf in 360 capture of unbounded scenes

Official implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021

Instant neural graphics primitives: lightning fast NeRF and more

Godot Engine – Multi-platform 2D and 3D game engine

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Deep Hough Voting for 3D Object Detection in Point Clouds

Code and models for "Pano3D: A Holistic Benchmark and a Solid Baseline for 360 Depth Estimation", OmniCV Workshop @ CVPR21.