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 f...Show MoreMetadata
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.
Date of Conference: 19-22 September 2021
Date Added to IEEE Xplore: 23 August 2021
ISBN Information: