Source code for "Interactive All-Hex Meshing via Cuboid Decomposition [SIGGRAPH Asia 2021]".

Overview

Interactive All-Hex Meshing via Cuboid Decomposition

teaser Video demonstration

This repository contains an interactive software to the PolyCube-based hex-meshing problem. You can solve hex meshing by playing minecraft!

Features include:

  • a 4-stage interactive pipeline that can robustly generate high-quality hex meshes from an input tetrahedral mesh;
  • extensive user control over each stage, such as editing the voxelized PolyCube, positioning surface vertices, and exploring the trade-off among competing quality metrics;
  • automatic alternatives based on GPU-powered continuous optimization that can run at interactive speed.

It is the original implementation of the SIGGRAPH Asia 2021 paper "Interactive All-Hex Meshing via Cuboid Decomposition" by Lingxiao Li, Paul Zhang, Dmitriy Smirnov, Mazdak Abulnaga, Justin Solomon. Check out our paper for a complete description of our pipeline!

Organization

There are three main components of the project.

  • The geomlib folder contains a standalone C++ library with GPU-based geometric operations including point-triangle projection (in arbitrary dimensions), point-tetrahedron projection (in arbitrary dimensions), point-in-tet-mesh inclusion testing, sampling on a triangular mesh, capable of handling tens of thousands of point queries on large meshes in milliseconds.
  • The vkoo folder contains a standalone object-oriented Vulkan graphics engine that is built based on the official Vulkan samples code with a lot of simplification and modification for the purpose of this project.
  • The hex folder contains the application-specific code for our interactive PolyCube-based hex meshing software, and should be most relevant for learning about the implementation details of our paper.

In addition,

  • results.zip contains the *.h5 project file and the *.mesh output hex mesh file for each model in the Table 2 of the paper. The *.h5 project files can be loaded in our software using File > Open.
  • The assets folder contains a small number of tetrahedral meshes to test on, but you can include your own meshes easily (if you only have triangular meshes, try using TetGen or this to mesh the interior first).
  • The external folder contains additional dependencies that are included in the repo.

Dependencies

Main dependencies that are not included in the repo and should be installed first:

  • CMake
  • CUDA (tested with 11.2, 11.3, 11.4, 11.5) and cuDNN
  • Pytorch C++ frontend (tested with 1.7, 1.8, 1.9, 1.10)
  • Vulkan SDK
  • Python3
  • HDF5

There are additional dependencies in external and should be built correctly with the provided CMake hierarchy:

  • Eigen
  • glfw
  • glm
  • glslang
  • imgui
  • spdlog
  • spirv-cross
  • stb
  • yaml-cpp

Linux Instruction

The instruction is slightly different on various Linux distributions. We have tested on Arch Linux and Ubuntu 20.04. First install all dependencies above using the respective package manager. Then download and unzip Pytorch C++ frontend for Linux (tested with cxx11 ABI) -- it should be under the tab Libtorch > C++/Java > CUDA 11.x. Add Torch_DIR=<unzipped folder> to your environment variable lists (or add your unzipped folder to CMAKE_PREFIX_PATH). Then clone the repo (be sure to use --recursive to clone the submodules as well). Next run the usual cmake/make commands to build target hex in Debug or Release mode:

mkdir -p build/Release
cd build/Release
cmake ../.. -DCMAKE_BUILD_TYPE=Release
make hex -j

This should generate an executable named hex under bin/Release/hex which can be run directly. See CMakeLists.txt for more information.

Windows Instruction

Compiling on Windows is trickier than on Linux. The following procedure has been tested to work on multiple Windows machines.

  • Download and install Visual Studio 2019
  • Download and install the newest CUDA Toolkit (tested with 11.2)
  • Download and install cuDNN for Windows (this amounts to copying a bunch of dll's to the CUDA path)
  • Download and install the newest Vulkan SDK binary for Windows
  • Download and install Python3
  • Download and unzip Pytorch C++ frontend for Windows. Then add TORCH_DIR=<unzipped folder> to your environment variable lists.
  • Download and install HDF5 for Windows
  • In VS2019, install CMake tools, and then build the project following this This should generate an executable under bin/Debug or bin/Release.
Owner
Lingxiao Li
Lingxiao Li
Self-Supervised CNN-GCN Autoencoder

GCNDepth Self-Supervised CNN-GCN Autoencoder GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network To be published

53 Dec 14, 2022
Collapse by Conditioning: Training Class-conditional GANs with Limited Data

Collapse by Conditioning: Training Class-conditional GANs with Limited Data Moha

Mohamad Shahbazi 33 Dec 06, 2022
nfelo: a power ranking, prediction, and betting model for the NFL

nfelo nfelo is a power ranking, prediction, and betting model for the NFL. Nfelo take's 538's Elo framework and further adapts it for the NFL, hence t

6 Nov 22, 2022
shufflev2-yolov5:lighter, faster and easier to deploy

shufflev2-yolov5: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size

pogg 1.5k Jan 05, 2023
Implement the Pareto Optimizer and pcgrad to make a self-adaptive loss for multi-task

multi-task_losses_optimizer Implement the Pareto Optimizer and pcgrad to make a self-adaptive loss for multi-task 已经实验过了,不会有cuda out of memory情况 ##Par

14 Dec 25, 2022
Code implementing "Improving Deep Learning Interpretability by Saliency Guided Training"

Saliency Guided Training Code implementing "Improving Deep Learning Interpretability by Saliency Guided Training" by Aya Abdelsalam Ismail, Hector Cor

8 Sep 22, 2022
Method for facial emotion recognition compitition of Xunfei and Datawhale .

人脸情绪识别挑战赛-第3名-W03KFgNOc-源代码、模型以及说明文档 队名:W03KFgNOc 排名:3 正确率: 0.75564 队员:yyMoming,xkwang,RichardoMu。 比赛链接:人脸情绪识别挑战赛 文章地址:link emotion 该项目分别训练八个模型并生成csv文

6 Oct 17, 2022
This is RFA-Toolbox, a simple and easy-to-use library that allows you to optimize your neural network architectures using receptive field analysis (RFA) and create graph visualizations of your architecture.

ReceptiveFieldAnalysisToolbox This is RFA-Toolbox, a simple and easy-to-use library that allows you to optimize your neural network architectures usin

84 Nov 23, 2022
PyTorch(Geometric) implementation of G^2GNN in "Imbalanced Graph Classification via Graph-of-Graph Neural Networks"

This repository is an official PyTorch(Geometric) implementation of G^2GNN in "Imbalanced Graph Classification via Graph-of-Graph Neural Networks". Th

Yu Wang (Jack) 13 Nov 18, 2022
Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.

TFLite-HITNET-Stereo-depth-estimation Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite. Stereo depth e

Ibai Gorordo 22 Oct 20, 2022
Flask101 - FullStack Web Development with Python & JS - From TAQWA

Task: Create a CLI Calculator Step 0: Creating Virtual Environment $ python -m

Hossain Foysal 1 May 31, 2022
SCNet: Learning Semantic Correspondence

SCNet Code Region matching code is contributed by Kai Han ([email protected]). Dense

Kai Han 34 Sep 06, 2022
BMN: Boundary-Matching Network

BMN: Boundary-Matching Network A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generatio

qinxin 260 Dec 06, 2022
Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Tom-R.T.Kvalvaag 2 Dec 17, 2021
1st-in-MICCAI2020-CPM - Combined Radiology and Pathology Classification

Combined Radiology and Pathology Classification MICCAI 2020 Combined Radiology a

22 Dec 08, 2022
Official implementation for “Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior”

Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior. The code will release soon. Implementation Python3 PyTorch=1.0 NVIDIA GPU+

FengZhang 34 Dec 04, 2022
Using deep actor-critic model to learn best strategies in pair trading

Deep-Reinforcement-Learning-in-Stock-Trading Using deep actor-critic model to learn best strategies in pair trading Abstract Partially observed Markov

281 Dec 09, 2022
Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19 (Oral).

Pose-Transfer Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19(Oral). The paper is available here. Video generation

Tengteng Huang 679 Jan 04, 2023
A Python library for Deep Probabilistic Modeling

Abstract DeeProb-kit is a Python library that implements deep probabilistic models such as various kinds of Sum-Product Networks, Normalizing Flows an

DeeProb-org 46 Dec 26, 2022
The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.

Human Trajectory Prediction via Counterfactual Analysis (CausalHTP) The official PyTorch code implementation of "Human Trajectory Prediction via Count

46 Dec 03, 2022