Clone a voice in 5 seconds to generate arbitrary speech in real-time

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.

StyleGAN2 - Official TensorFlow Implementation

High-Resolution 3D Human Digitization from A Single Image.

Model parallel transformers in JAX and Haiku

This repo contains source code and materials for the TEmporally COherent GAN SIGGRAPH project.

Learning to See in the Dark. CVPR 2018

StyleGAN2-ADA - Official PyTorch implementation

NVIDIA's Deep Imagination Team's PyTorch Library

Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

Just draw a bounding box and you can remove the object you want to remove.

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

A PyTorch library and evaluation platform for end-to-end compression research

TRI-ML Monocular Depth Estimation Repository

Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.

Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

Official implementation of Joint Monocular 3D Vehicle Detection and Tracking (ICCV 2019)

(ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

Repository relating to the CVPR21 paper TimeLens: Event-based Video Frame Interpolation

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

Hybrid Neural Fusion for Full-frame Video Stabilization

Official implementation of Monocular Quasi-Dense 3D Object Tracking, TPAMI 2022

Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

This repository contains code and dataset for the task crack segmentation using two architectures UNet_VGG16, UNet_Resnet and DenseNet-Tiramusu

Python Wrappers for SWMM

PyTorch implementations for our SIGGRAPH 2021 paper: Editable Free-viewpoint Video Using a Layered Neural Representation.