Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

This repository contains a reference implementation of our Part-Aware Data Augmentation for 3D Object Detection in Point Cloud.

If you find this code useful in your research, please consider citing our work:

@article{choi2020part,
  title={Part-Aware Data Augmentation for 3D Object Detection in Point Cloud},
  author={Choi, Jaeseok and Song, Yeji and Kwak, Nojun},
  journal={arXiv preprint arXiv:2007.13373},
  year={2020}
}

Prerequisites

Our code was tested on second.pytorch and OpenPCDet.
This repository contains only part-aware data augmentation code.
Refer to the link above for code such as data loader or detector.

Usage

Args:
    ** only supports KITTI format **
    points: lidar points (N, 4), 
    gt_boxes: ground truth boxes (B, 7),
    gt_names: ground truth classes (B, 1), 
    class_names: list of classes to augment (3),
    pa_aug_param: parameters for PA_AUG (string).

Returns:
    points: augmented lidar points (N', 4),
    gt_boxes_mask: mask for gt_boxes (B)


class_names = ['Car', 'Pedestrian', 'Cyclist']
pa_aug_param = "dropout_p02_swap_p02_mix_p02_sparse40_p01_noise10_p01"

pa_aug = PartAwareAugmentation(points, gt_boxes, gt_names, class_names=class_names)
points, gt_boxes_mask = pa_aug.augment(pa_aug_param=pa_aug_param)
gt_boxes = gt_boxes[gt_boxes_mask]

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

Related tags

Overview

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

Prerequisites

Usage

Owner

Jaeseok Choi

Prototypical Networks for Few shot Learning in PyTorch

This program was designed to detect whether someone is wearing a facemask through a live video stream.

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation

PyTorch implementation of Constrained Policy Optimization

Parameterising Simulated Annealing for the Travelling Salesman Problem

PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML)

Federated Learning - Including common test models for federated learning, like CNN, Resnet18 and lstm, controlled by different parser

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

Python utility to generate filesystem content for Obsidian.

Catbird is an open source paraphrase generation toolkit based on PyTorch.

Video Matting via Consistency-Regularized Graph Neural Networks

An Unpaired Sketch-to-Photo Translation Model

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

This is the repository for The Machine Learning Workshops, published by AI DOJO

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

TalkingHead-1KH is a talking-head dataset consisting of YouTube videos

Stock-history-display - something like a easy yearly review for your stock performance

Image Matching Evaluation

Code and Datasets from the paper "Self-supervised contrastive learning for volcanic unrest detection from InSAR data"

Detecting Blurred Ground-based Sky/Cloud Images