Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

Nightly release of ControlNet 1.1

Make human motion capture easier.

Free Motion Capture for Everyone 💀✨

[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

Real-time pose estimation accelerated with NVIDIA TensorRT

[CVPR 2021] Self-supervised depth estimation from short sequences

Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)

Hybrid Neural Fusion for Full-frame Video Stabilization

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Code release for HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling

Neural Light Transport for Relighting and View Synthesis

[ICCV 2021 Oral] Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

InverseRenderNet: Learning single image inverse rendering, CVPR 2019.

Official PyTorch implementation of "Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss" (SIGGRAPH 2020)

A cross platform GUI for youtube-dl written entirely in python using the WX library.

Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

Human Performance Capture from Monocular Video in the Wild (3DV2021)

Enforcing Temporal Consistency in Video Depth Estimation, ICCV-W 2021.

Implementation of "Outdoor inverse rendering from a single image using multiview self-supervision"

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

Code for "NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decomposition in Indoor Scenes" TVCG

Official model and network release for my CVPR2022 paper.