Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

Introduction to blender scripting

A module to simplify the use of the Blender Python API.

Content-Aware Unsupervised Deep Homography Estimation

An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.

The official PyTorch implementation of the paper: *Xili Dai, Xiaojun Yuan, Haigang Gong, Yi Ma. "Fully Convolutional Line Parsing." *.

Relative Human dataset, CVPR 2022

Simulated garment dataset for virtual try-on

Learning-Based Animation of Clothing for Virtual Try-On

Official implementation of Generating Datasets of 3D Garments with Sewing Patterns

Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On