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
GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.

2.3k Jan 09, 2023
Shallow Convolutional Neural Networks for Human Activity Recognition using Wearable Sensors

-IEEE-TIM-2021-1-Shallow-CNN-for-HAR [IEEE TIM 2021-1] Shallow Convolutional Neural Networks for Human Activity Recognition using Wearable Sensors All

Wenbo Huang 1 May 17, 2022
Implements an infinite sum of poisson-weighted convolutions

An infinite sum of Poisson-weighted convolutions Kyle Cranmer, Aug 2018 If viewing on GitHub, this looks better with nbviewer: click here Consider a v

Kyle Cranmer 26 Dec 07, 2022
Implementation of Basic Machine Learning Algorithms on small datasets using Scikit Learn.

Basic Machine Learning Algorithms All the basic Machine Learning Algorithms are implemented in Python using libraries Acknowledgements Machine Learnin

Piyal Banik 47 Oct 16, 2022
One implementation of the paper "DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing".

Introduction One implementation of the paper "DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing". Users

seq-to-mind 18 Dec 11, 2022
Computer Vision and Pattern Recognition, NUS CS4243, 2022

CS4243_2022 Computer Vision and Pattern Recognition, NUS CS4243, 2022 Cloud Machine #1 : Google Colab (Free GPU) Follow this Notebook installation : h

Xavier Bresson 142 Dec 15, 2022
PromptDet: Expand Your Detector Vocabulary with Uncurated Images

PromptDet: Expand Your Detector Vocabulary with Uncurated Images Paper Website Introduction The goal of this work is to establish a scalable pipeline

103 Dec 20, 2022
Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

NeX: Real-time View Synthesis with Neural Basis Expansion Project Page | Video | Paper | COLAB | Shiny Dataset We present NeX, a new approach to novel

536 Dec 20, 2022
ColossalAI-Examples - Examples of training models with hybrid parallelism using ColossalAI

ColossalAI-Examples This repository contains examples of training models with Co

HPC-AI Tech 185 Jan 09, 2023
[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax

[NeurIPS 2021] Galerkin Transformer: linear attention without softmax Summary A non-numerical analyst oriented explanation on Toward Data Science abou

Shuhao Cao 159 Dec 20, 2022
Torch-based tool for quantizing high-dimensional vectors using additive codebooks

Trainable multi-codebook quantization This repository implements a utility for use with PyTorch, and ideally GPUs, for training an efficient quantizer

Daniel Povey 41 Jan 07, 2023
CenterNet:Objects as Points目标检测模型在Pytorch当中的实现

CenterNet:Objects as Points目标检测模型在Pytorch当中的实现

Bubbliiiing 267 Dec 29, 2022
P-Tuning v2: Prompt Tuning Can Be Comparable to Finetuning Universally Across Scales and Tasks

P-tuning v2 P-Tuning v2: Prompt Tuning Can Be Comparable to Finetuning Universally Across Scales and Tasks An optimized prompt tuning strategy achievi

THUDM 540 Dec 30, 2022
TCNN Temporal convolutional neural network for real-time speech enhancement in the time domain

TCNN Pandey A, Wang D L. TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain[C]//ICASSP 2019-2019 IEEE Int

凌逆战 16 Dec 30, 2022
Conformer: Local Features Coupling Global Representations for Visual Recognition

Conformer: Local Features Coupling Global Representations for Visual Recognition (arxiv) This repository is built upon DeiT and timm Usage First, inst

Zhiliang Peng 378 Jan 08, 2023
Distributed Asynchronous Hyperparameter Optimization in Python

Hyperopt: Distributed Hyperparameter Optimization Hyperopt is a Python library for serial and parallel optimization over awkward search spaces, which

6.5k Jan 01, 2023
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning Preprocess file of the dataset used in implicit sub-populations: (Demographic groups

<a href=[email protected]"> 4 Oct 14, 2022
realsense d400 -> jpg + csv

Realsense-capture realsense d400 - jpg + csv Requirements RealSense sdk : Installation Python3 pyrealsense2 (RealSense SDK) Numpy OpenCV Tkinter Run

Ar-Ray 2 Mar 22, 2022
Collection of NLP model explanations and accompanying analysis tools

Thermostat is a large collection of NLP model explanations and accompanying analysis tools. Combines explainability methods from the captum library wi

126 Nov 22, 2022
A solution to the 2D Ising model of ferromagnetism, implemented using the Metropolis algorithm

Solving the Ising model on a 2D lattice using the Metropolis Algorithm Introduction The Ising model is a simplified model of ferromagnetism, the pheno

Rohit Prabhu 5 Nov 13, 2022