-
UC Berkeley
- https://people.eecs.berkeley.edu/~zhecao/
Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A library for efficient similarity search and clustering of dense vectors.
A toolkit for developing and comparing reinforcement learning algorithms.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Productive, portable, and performant GPU programming in Python.
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Command & Conquer: Remastered Collection
🎮 A step-by-step guide to implementing SSAO, depth of field, lighting, normal mapping, and more for your 3D game.
Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS, and WebGL2
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Datasets, Transforms and Models specific to Computer Vision
Face recognition with deep neural networks.
Ongoing research training transformer models at scale
Open-source simulator for autonomous driving research.
Open3D: A Modern Library for 3D Data Processing
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Image-to-image translation with conditional adversarial nets
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
COLMAP - Structure-from-Motion and Multi-View Stereo
Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511
TensorFlow-based neural network library
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
⚡ Hugo Blox: Markdown sites in minutes. Academic/resume/lab/portfolio for AI researchers & startups. Premium templates. Deploy to GitHub Pages now in 1-click 👇
Caffe2 is a lightweight, modular, and scalable deep learning framework.
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.
Object detection, 3D detection, and pose estimation using center point detection: