Stars
GLIDE: a diffusion-based text-conditional image synthesis model
A latent text-to-image diffusion model
A set of utilities for taking the pain out of Vulkan in header only modern C++
Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)
NVIDIA Linux open GPU kernel module source
Reversing Google's 3D satellite mode
A tool for exploring each layer in a docker image
A C++ standalone library for machine learning
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A series of experiments on terrain and elevation data for Tangram
Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"
Toward Multimodal Image-to-Image Translation
'Good' GStreamer plugins and helper libraries. This module has been merged into the main GStreamer repo for further development.
References(in PDF format) for SVO SLAM; mostly in PDF format.
This is the python interface for adapted COLMAP; you can run both SfM and MVS.
Arbitrary dimensional level sets
stb single-file public domain libraries for C/C++
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Computer generated building footprints for Canada
Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]
Starting kit for AutoCV/AutoDL challenge (https://autodl.chalearn.org)
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
Code release for "learning to find good correspondences" CVPR 2018
Proposes neural networks that can generate animation of virtual characters for different actions.