The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Last update: Dec 26, 2022

Related tags

Deep Learning CSGStumpNet

Overview

CSGStumpNet

The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Paper | Project page

Citation

If you find our work interesting and benifits your research, please consider citing:

@article{ren2021csgstump,
  title={CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing},
  author={Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, Shuai Yi},
  journal={ICCV},
  year={2021}
}

Setup

Install envoriment:

We recommand using Anaconda to set the envoriment, once Anacodna in installed, run the following command.

conda create --name CSGStumpNet python=3.7
conda activate CSGStumpNet
conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=10.1 -c pytorch
conda install -c open3d-admin open3d=0.9
conda install numpy
conda install pymcubes
conda install tensorboard
conda install scipy
pip install tqdm

Datasets and pre-trained weights

Dataset

We use the pre-prepared dataset from OccNet(consider citing them), you can download the data by

mkdir data
cd data
wget https://s3.eu-central-1.amazonaws.com/avg-projects/occupancy_networks/data/dataset_small_v1.1.zip
unzip dataset_small_v1.1.zip

If you want to prepare data yourself (maybe you want to generate the watertight mesh etc.), please refer to this link.

Pre-Train Weights

The original trained weights are no longer compatiable with the the restructred code (this repo) :( re-training is in progress (This may take some time).

Evaluate using pre-trian weights

python eval.py --config_path ./configs/plane_256_256.json

Train from stratch

python train.py --config_path ./configs/plane_256_256.json

Evaluation

python metrics.py --config_path ./configs/plane_256_256.json

License

This project is licensed under the terms of the MIT license (see LICENSE for details).

The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Related tags

Overview

CSGStumpNet

Paper | Project page

Citation

Setup

Install envoriment:

Datasets and pre-trained weights

Dataset

Pre-Train Weights

Evaluate using pre-trian weights

Train from stratch

Evaluation

License

Owner

Daxuan

Cards Against Humanity AI

Transfer Learning Remote Sensing

Code for our TKDE paper "Understanding WeChat User Preferences and “Wow” Diffusion"

ALBERT-pytorch-implementation - ALBERT pytorch implementation

Geometric Algebra package for JAX

Codes for Causal Semantic Generative model (CSG), the model proposed in "Learning Causal Semantic Representation for Out-of-Distribution Prediction" (NeurIPS-21)

Pytoydl: A toy deep learning framework built upon numpy.

Oriented Response Networks, in CVPR 2017

An implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

Human motion synthesis using Unity3D

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

🕵 Artificial Intelligence for social control of public administration

PyTorch code of my WACV 2022 paper Improving Model Generalization by Agreement of Learned Representations from Data Augmentation

official implemntation for "Contrastive Learning with Stronger Augmentations"

TensorFlow implementation of Elastic Weight Consolidation

Code release for NeRF (Neural Radiance Fields)

Codes of the paper Deformable Butterfly: A Highly Structured and Sparse Linear Transform.

Making a music video with Wav2CLIP and VQGAN-CLIP

The official repo for CVPR2021——ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search.