arxivst stuff from arxiv that you should probably bookmark

3d Point Cloud Dataset and Benchmark

Post · Apr 13, 2017 15:55 ·

dataset 3d point-cloud semantic3d cs-cv cs-lg cs-ne cs-ro

New 3d point cloud dataset and benchmark with semantic labels. Should be a lot of use to people doing AR. They did a nice job with the benchmark too, and have an automated submission process with a public leaderboard.

Highlights From the Paper

  • 4x10^9 points and class labels for 8 classes. The data set is split into training and test sets of approximately equal size.
  • 30 published terrestrial laser scans consist of in total ≈ 4 billion 3D points and contain urban and rural scenes, like farms, town halls, sport fields, a castle and market squares
  • Baseline for the point cloud classification task follow(s) recent VoxNet (Maturana and Scherer, 2015) and ShapeNet (Wu et al., 2015) 3D encoding ideas. Code

Datasets

semantic3D.net

Arxiv Abstract

  • Timo Hackel
  • Nikolay Savinov
  • Lubor Ladicky
  • Jan D. Wegner
  • Konrad Schindler
  • Marc Pollefeys

This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that use deep convolutional neural networks (CNNs) as a work horse, which already show remarkable performance improvements over state-of-the-art. CNNs have become the de-facto standard for many tasks in computer vision and machine learning like semantic segmentation or object detection in images, but have no yet led to a true breakthrough for 3D point cloud labelling tasks due to lack of training data. With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks. Our [semantic3D.net](http://semantic3D.net) data set consists of dense point clouds acquired with static terrestrial laser scanners. It contains 8 semantic classes and covers a wide range of urban outdoor scenes: churches, streets, railroad tracks, squares, villages, soccer fields and castles. We describe our labelling interface and show that our data set provides more dense and complete point clouds with much higher overall number of labelled points compared to those already available to the research community. We further provide baseline method descriptions and comparison between methods submitted to our online system. We hope semantic3D.net will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case.

Read the paper (pdf) »