Semantic Segmentation in Depth Data: A Comparative Evaluation of Image and Point Cloud Based Methods

Jigyasa Singh Katrolia, Lars Krämer, Jason R. Rambach, Bruno Mirbach, Didier StrickerICIP 2021 · OpenReview

Abstract

The problem of semantic segmentation from depth images can be addressed by segmenting directly in the image domain or at 3D point cloud level. In this paper, we attempt for the first time to provide a study and experimental comparison of the two approaches. Through experiments on three datasets, namely SUN RGB-D, NYUdV2 and TICaM, we extensively compare various semantic segmentation algorithms, the input to which includes images and point clouds derived from them. Based on this, we offer analysis of the performance and computational cost of these algorithms that can provide guidelines on when each method should be preferred.
BibTeX
@inproceedings{katrolia2021semantic,
  author = {Jigyasa Singh Katrolia and Lars Krämer and Jason R. Rambach and Bruno Mirbach and Didier Stricker},
  title = {{Semantic Segmentation in Depth Data: A Comparative Evaluation of Image and Point Cloud Based Methods}},
  booktitle = {ICIP},
  year = {2021},
  url = {https://openreview.net/forum?id=miB5D9PKrrf},
}

Loading related content...

Figure