Pytorch implementation for "Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion" (NeurIPS 2021)

Overview

Density-aware Chamfer Distance

This repository contains the official PyTorch implementation of our paper:

Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion, NeurIPS 2021

Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang, Ziwei Liu, Dahua Lin

avatar

We present a new point cloud similarity measure named Density-aware Chamfer Distance (DCD). It is derived from CD and benefits from several desirable properties: 1) it can detect disparity of density distributions and is thus a more intensive measure of similarity compared to CD; 2) it is stricter with detailed structures and significantly more computationally efficient than EMD; 3) the bounded value range encourages a more stable and reasonable evaluation over the whole test set. DCD can be used as both an evaluation metric and the training loss. We mainly validate its performance on point cloud completion in our paper.

This repository includes:

  • Implementation of Density-aware Chamfer Distance (DCD).
  • Implementation of our method for this task and the pre-trained model.

Installation

Requirements

  • PyTorch 1.2.0
  • Open3D 0.9.0
  • Other dependencies are listed in requirements.txt.

Install

Install PyTorch 1.2.0 first, and then get the other requirements by running the following command:

bash setup.sh

Dataset

We use the MVP Dataset. Please download the train set and test set and then modify the data path in data/mvp_new.py to the your own data location. Please refer to their codebase for further instructions.

Usage

Density-aware Chamfer Distance

The function for DCD calculation is defined in def calc_dcd() in utils/model_utils.py.

Users of higher PyTorch versions may try def calc_dcd() in utils_v2/model_utils.py, which has been tested on PyTorch 1.6.0 .

Model training and evaluation

  • To train a model: run python train.py ./cfgs/*.yaml, for example:
python train.py ./cfgs/vrc_plus.yaml
  • To test a model: run python train.py ./cfgs/*.yaml --test_only, for example:
python train.py ./cfgs/vrc_plus_eval.yaml --test_only
  • Config for each algorithm can be found in cfgs/.
  • run_train.sh and run_test.sh are provided for SLURM users.

We provide the following config files:

  • pcn.yaml: PCN trained with CD loss.
  • vrc.yaml: VRCNet trained with CD loss.
  • pcn_dcd.yaml: PCN trained with DCD loss.
  • vrc_dcd.yaml: VRCNet trained with DCD loss.
  • vrc_plus.yaml: training with our method.
  • vrc_plus_eval.yaml: evaluation of our method with guided down-sampling.

Attention: We empirically find that using DP or DDP for training would slightly hurt the performance. So training on multiple cards is not well supported currently.

Pre-trained models

We provide the pre-trained model that reproduce the results in our paper. Download and extract it to the ./log/pretrained/ directory, and then evaluate it with cfgs/vrc_plus_eval.yaml. The setting prob_sample: True turns on the guided down-sampling. We also provide the model for VRCNet trained with DCD loss here.

Citation

If you find our code or paper useful, please cite our paper:

@inproceedings{wu2021densityaware,
  title={Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion},
  author={Tong Wu, Liang Pan, Junzhe Zhang, Tai WANG, Ziwei Liu, Dahua Lin},
  booktitle={In Advances in Neural Information Processing Systems (NeurIPS), 2021},
  year={2021}
}

Acknowledgement

The code is based on the VRCNet implementation. We include the following PyTorch 3rd-party libraries: ChamferDistancePytorch, emd, expansion_penalty, MDS, and Pointnet2.PyTorch. Thanks for these great projects.

Contact

Please contact @wutong16 for questions, comments and reporting bugs.

Owner
Tong WU
Tong WU
Code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search.

TransNAS-Bench-101 This repository contains the publishable code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizabili

Yawen Duan 17 Nov 20, 2022
Contrastive Fact Verification

VitaminC This repository contains the dataset and models for the NAACL 2021 paper: Get Your Vitamin C! Robust Fact Verification with Contrastive Evide

47 Dec 19, 2022
A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

AnimeGAN A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing. Randomly Generated Images The images are

Jie Lei 雷杰 1.2k Jan 03, 2023
Pytorch implementation for "Open Compound Domain Adaptation" (CVPR 2020 ORAL)

Open Compound Domain Adaptation [Project] [Paper] [Demo] [Blog] Overview Open Compound Domain Adaptation (OCDA) is the author's re-implementation of t

Zhongqi Miao 137 Dec 15, 2022
GoodNews Everyone! Context driven entity aware captioning for news images

This is the code for a CVPR 2019 paper, called GoodNews Everyone! Context driven entity aware captioning for news images. Enjoy! Model preview: Huge T

117 Dec 19, 2022
Image De-raining Using a Conditional Generative Adversarial Network

Image De-raining Using a Conditional Generative Adversarial Network [Paper Link] [Project Page] He Zhang, Vishwanath Sindagi, Vishal M. Patel In this

He Zhang 216 Dec 18, 2022
Improving Calibration for Long-Tailed Recognition (CVPR2021)

MiSLAS Improving Calibration for Long-Tailed Recognition Authors: Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia [arXiv] [slide] [BibTeX] Introductio

Jia Research Lab 116 Dec 20, 2022
Official PyTorch implementation of the paper: DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample (ICCV 2021 Oral) Project | Paper Official PyTorch implementation of the pape

Eliahu Horwitz 393 Dec 22, 2022
ProjectOxford-ClientSDK - This repo has moved :house: Visit our website for the latest SDKs & Samples

This project has moved 🏠 We heard your feedback! This repo has been deprecated and each project has moved to a new home in a repo scoped by API and p

Microsoft 970 Nov 28, 2022
Official DGL implementation of "Rethinking High-order Graph Convolutional Networks"

SE Aggregation This is the implementation for Rethinking High-order Graph Convolutional Networks. Here we show the codes for citation networks as an e

Tianqi Zhang (张天启) 32 Jul 19, 2022
Adversarial Graph Augmentation to Improve Graph Contrastive Learning

ADGCL : Adversarial Graph Augmentation to Improve Graph Contrastive Learning Introduction This repo contains the Pytorch [1] implementation of Adversa

susheel suresh 62 Nov 19, 2022
Language model Prompt And Query Archive

LPAQA: Language model Prompt And Query Archive This repository contains data and code for the paper How Can We Know What Language Models Know? Install

127 Dec 20, 2022
NeuralForecast is a Python library for time series forecasting with deep learning models

NeuralForecast is a Python library for time series forecasting with deep learning models. It includes benchmark datasets, data-loading utilities, evaluation functions, statistical tests, univariate m

Nixtla 1.1k Jan 03, 2023
Multimodal Co-Attention Transformer (MCAT) for Survival Prediction in Gigapixel Whole Slide Images

Multimodal Co-Attention Transformer (MCAT) for Survival Prediction in Gigapixel Whole Slide Images [ICCV 2021] © Mahmood Lab - This code is made avail

Mahmood Lab @ Harvard/BWH 63 Dec 01, 2022
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Vision Transformer Pytorch reimplementation of Google's repository for the ViT model that was released with the paper An Image is Worth 16x16 Words: T

Eunkwang Jeon 1.4k Dec 28, 2022
🔥3D-RecGAN in Tensorflow (ICCV Workshops 2017)

3D Object Reconstruction from a Single Depth View with Adversarial Learning Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni

Bo Yang 125 Nov 26, 2022
Simple implementation of OpenAI CLIP model in PyTorch.

It was in January of 2021 that OpenAI announced two new models: DALL-E and CLIP, both multi-modality models connecting texts and images in some way. In this article we are going to implement CLIP mod

Moein Shariatnia 226 Jan 05, 2023
FaceAPI: AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using TensorFlow/JS

FaceAPI AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using

Vladimir Mandic 395 Dec 29, 2022
Improving Calibration for Long-Tailed Recognition (CVPR2021)

MiSLAS Improving Calibration for Long-Tailed Recognition Authors: Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia [arXiv] [slide] [BibTeX] Introductio

DV Lab 116 Dec 20, 2022
The Ludii general game system, developed as part of the ERC-funded Digital Ludeme Project.

The Ludii General Game System Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP). This repository h

Digital Ludeme Project 50 Jan 04, 2023