Code for [CVPR 2025] GenVDM:Generating Vector Displacement Maps From a Single Image

🌎 Real time wallpaper engine for Windows and macOS

🥜 Header-only C++20 matrix library using expression templates

Code for Brep2Seq: a dataset and hierarchical deep learning network for reconstruction and generation of computer-aided design models.

Official implentation of "Ghost on the Shell: An Expressive Representation of General 3D Shapes" (ICLR 2024 Oral)

Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)

[ECCV 2022] Monocular 3D Object Reconstruction with GAN Inversion

onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime

Realtime TensorFlow.js + WebGL visualization apps. 3D Hand pose estimation, 3D Human pose estimation, Face swap, Depth estimation, Higher accuracy face detection.

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…

🍭 Simple physically-based offline renderer

Collection of vtk.js based cinematic rendering experiments.

unofficial code of the paper "Efficient Geometry-aware 3D Generative Adversarial Networks"

[CVPR2022] Neural Rays for Occlusion-aware Image-based Rendering

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

👦 👧 Technical-Interview guidelines written for those who started studying programming. I wish you all the best. 👾

Convert Caffe models to ONNX.

A large-scale face dataset for face parsing, recognition, generation and editing.

Official implementation of CVPR2020 paper "Learning to Dress 3D People in Generative Clothing" https://arxiv.org/abs/1907.13615

SvelteKit implementation of the RealWorld app

C++ implementation of Embedded Deformation for Shape Manipulation

CoSMA: Convolutional Semi-Regular Mesh Autoencoder. Accepted at WACV 2022

Template for building basic applications with Svelte

CenterHMR: a bottom-up single-shot method for multi-person 3D mesh recovery from a single image