Code for "Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks", CVPR 2021

Overview

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

Example 1 Example 2 Example 3

This repository contains the code that accompanies our CVPR 2021 paper Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

You can find detailed usage instructions for training your own models and using our pretrained models below.

If you found this work influential or helpful for your research, please consider citing

@Inproceedings{Paschalidou2021CVPR,
     title = {Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks},
     author = {Paschalidou, Despoina and Katharopoulos, Angelos and Geiger, Andreas and Fidler, Sanja},
     booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
     year = {2021}
}

Installation & Dependencies

Our codebase has the following dependencies:

For the visualizations, we use simple-3dviz, which is our easy-to-use library for visualizing 3D data using Python and ModernGL and matplotlib for the colormaps. Note that simple-3dviz provides a lightweight and easy-to-use scene viewer using wxpython. If you wish you use our scripts for visualizing the reconstructed primitives, you will need to also install wxpython.

The simplest way to make sure that you have all dependencies in place is to use conda. You can create a conda environment called neural_parts using

conda env create -f environment.yaml
conda activate neural_parts

Next compile the extenstion modules. You can do this via

python setup.py build_ext --inplace
pip install -e .

Demo

Example Output Example Output

You can now test our code on various inputs. To this end, simply download some input samples together with our pretrained models on D-FAUAST humans, ShapeNet chairs and ShapeNet planes from here. Now extract the nerual_parts_demo.zip that you just downloaded in the demo folder. To run our demo on the D-FAUST humans simply run

python demo.py ../config/dfaust_6.yaml --we ../demo/model_dfaust_6 --model_tag 50027_jumping_jacks:00135 --camera_target='-0.030173788,-0.10342446,-0.0021887198' --camera_position='0.076685235,-0.14528269,1.2060229' --up='0,1,0' --with_rotating_camera

This script should create a folder demo/output, where the per-primitive meshes are stored as .obj files. Similarly, you can now also run the demo for the input airplane

python demo.py ../config/shapenet_5.yaml --we ../demo/model_planes_5 --model_tag 02691156:7b134f6573e7270fb0a79e28606cb167 --camera_target='-0.030173788,-0.10342446,-0.0021887198' --camera_position='0.076685235,-0.14528269,1.2060229' --up='0,1,0' --with_rotating_camera

Usage

As soon as you have installed all dependencies and have obtained the preprocessed data, you can now start training new models from scratch, evaluate our pre-trained models and visualize the recovered primitives using one of our pre-trained models.

Reconstruction

To generate meshes using a trained model, we provide the forward_pass.py and the visualize_predictions.py scripts. Their difference is that the first performs the forward pass and generates a per-primitive mesh that is saved as an .obj file. Similarly, the visualize_predictions.py script performs the forward pass and visualizes the predicted primitives using simple-3dviz. The forward_pass.py script is ideal for reconstructing inputs on a heeadless server and you can run it by executing

python forward_pass.py path_to_config_yaml path_to_output_dir --weight_file path_to_weight_file --model_tag MODEL_TAG

where the argument --weight_file specifies the path to a trained model and the argument --model_tag defines the model_tag of the input to be reconstructed.

To run the visualize_predictions.py script you need to run

python visualize_predictions.py path_to_config_yaml path_to_output_dir --weight_file path_to_weight_file --model_tag MODEL_TAG

Using this script, you can easily render the prediction into .png images or a .gif, as well as perform various animations by rotating the camera. Furthermore, you can also specify the camera position, the up vector and the camera target as well as visualize the target mesh together with the predicted primitives simply by adding the --mesh argument.

Evaluation

For evaluation of the models we provide the script evaluate.py. You can run it using:

python evaluate.py path_to_config_yaml path_to_output_dir

The script reconstructs the input and evaluates the generated meshes using a standardized protocol. For each input, the script generates a .npz file that contains the various metrics for that particular input. Note that this script can also be executed multiple times in order to speed up the evaluation process. For example, if you wish to run the evaluation on 6 nodes, you can simply run

for i in {1..6}; do python evaluate.py path_to_config_yaml path_to_output_dir & done
[1] 9489
[2] 9490
[3] 9491
[4] 9492
[5] 9493
[6] 9494

wait
Running code on cpu
Running code on cpu
Running code on cpu
Running code on cpu
Running code on cpu
Running code on cpu

Again the script generates a per-input file in the output directory with the computed metrics.

Training

Finally, to train a new network from scratch, we provide the train_network.py script. To execute this script, you need to specify the path to the configuration file you wish to use and the path to the output directory, where the trained models and the training statistics will be saved. Namely, to train a new model from scratch, you simply need to run

python train_network.py path_to_config_yaml path_to_output_dir

Note tha it is also possible to start from a previously trained model by specifying the --weight_file argument, which should contain the path to a previously trained model. Furthermore, by using the arguments --model_tag and --category_tag, you can also train your network on a particular model (e.g. a specific plane, car, human etc.) or a specific object category (e.g. planes, chairs etc.)

Note that, if you want to use the RAdam optimizer during training, you will have to also install to download and install the corresponding code from this repository.

License

Our code is released under the MIT license which practically allows anyone to do anything with it. MIT license found in the LICENSE file.

Relevant Research

Below we list some papers that are relevant to our work.

Ours:

  • Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image pdf,project-page
  • Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids pdf,project-page

By Others:

  • Learning Shape Abstractions by Assembling Volumetric Primitives pdf
  • 3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks pdf
  • Im2Struct: Recovering 3D Shape Structure From a Single RGB Image pdf
  • Learning shape templates with structured implicit functions pdf
  • CvxNet: Learnable Convex Decomposition pdf
Xintao 1.4k Dec 25, 2022
Pytorch implementation of Nueral Style transfer

Nueral Style Transfer Pytorch implementation of Nueral style transfer algorithm , it is used to apply artistic styles to content images . Content is t

Abhinav 9 Oct 15, 2022
School of Artificial Intelligence at the Nanjing University (NJU)School of Artificial Intelligence at the Nanjing University (NJU)

F-Principle This is an exercise problem of the digital signal processing (DSP) course at School of Artificial Intelligence at the Nanjing University (

Thyrix 5 Nov 23, 2022
Explaining Hyperparameter Optimization via PDPs

Explaining Hyperparameter Optimization via PDPs This repository gives access to an implementation of the methods presented in the paper submission “Ex

2 Nov 16, 2022
Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Dangers of Bayesian Model Averaging under Covariate Shift This repository contains the code to reproduce the experiments in the paper Dangers of Bayes

Pavel Izmailov 25 Sep 21, 2022
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Poincaré Embeddings for Learning Hierarchical Representations PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations

Facebook Research 1.6k Dec 25, 2022
A hifiasm fork for metagenome assembly using Hifi reads.

hifiasm_meta - de novo metagenome assembler, based on hifiasm, a haplotype-resolved de novo assembler for PacBio Hifi reads.

44 Jul 10, 2022
Build and run Docker containers leveraging NVIDIA GPUs

NVIDIA Container Toolkit Introduction The NVIDIA Container Toolkit allows users to build and run GPU accelerated Docker containers. The toolkit includ

NVIDIA Corporation 15.6k Jan 01, 2023
9th place solution in "Santa 2020 - The Candy Cane Contest"

Santa 2020 - The Candy Cane Contest My solution in this Kaggle competition "Santa 2020 - The Candy Cane Contest", 9th place. Basic Strategy In this co

toshi_k 22 Nov 26, 2021
Teaching end to end workflow of deep learning

Deep-Education This repository is now available for public use for teaching end to end workflow of deep learning. This implies that learners/researche

Data Lab at College of William and Mary 2 Sep 26, 2022
Repository for the NeurIPS 2021 paper: "Exploiting Domain-Specific Features to Enhance Domain Generalization".

meta-Domain Specific-Domain Invariant (mDSDI) Source code implementation for the paper: Manh-Ha Bui, Toan Tran, Anh Tuan Tran, Dinh Phung. "Exploiting

VinAI Research 12 Nov 25, 2022
This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

TransMix: Attend to Mix for Vision Transformers This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transf

Jie-Neng Chen 130 Jan 01, 2023
(SIGIR2020) “Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback’’

Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback About This repository accompanies the real-world experiments conducted i

yuta-saito 19 Dec 01, 2022
学习 python3 以来写的一些垃圾玩具……

和东哥做兄弟 Author: chiupam 版权 未经本人同意,仓库内所有资源文件,禁止任何公众号、自媒体、开发者进行任何形式的转载、发布、搬运。 声明 这不是一个开源项目,只是把 GitHub 当作一个代码的存储空间,本项目不接受任何开源要求。 仅用于学习研究,禁止用于商业用途,不能保证其合法性

Chiupam 67 Mar 26, 2022
Shōgun

The SHOGUN machine learning toolbox Unified and efficient Machine Learning since 1999. Latest release: Cite Shogun: Develop branch build status: Donat

Shōgun ML 2.9k Jan 04, 2023
This repository lets you interact with Lean through a REPL.

lean-gym This repository lets you interact with Lean through a REPL. See Formal Mathematics Statement Curriculum Learning for a presentation of lean-g

OpenAI 87 Dec 28, 2022
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dea

MIC-DKFZ 1.2k Jan 04, 2023
Code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection"

CTDNet The PyTorch code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection" Requirements Python 3.6

CVTEAM 28 Oct 20, 2022
Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

LMSOC: An Approach for Socially Sensitive Pretraining Code for reproducing the paper LMSOC: An Approach for Socially Sensitive Pretraining to appear a

Twitter Research 11 Dec 20, 2022
Using machine learning to predict undergrad college admissions.

College-Prediction Project- Overview: Many have tried, many have failed. Few trailblazers are ambitious enought to chase acceptance into the top 15 un

John H Klinges 1 Jan 05, 2022