TY - GEN
T1 - Evaluating the Impact of Point Cloud Colorization on Semantic Segmentation Accuracy
AU - Zhu, Qinfeng
AU - Cao, Jiaze
AU - Cai, Yuanzhi
AU - Fan, Lei
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Point cloud semantic segmentation, the process of classifying each point into predefined categories, is essential for 3D scene understanding. While image-based segmentation is widely adopted due to its maturity, methods relying solely on RGB information often suffer from degraded performance due to color inaccuracies. Recent advancements have incorporated additional features such as intensity and geometric information, yet RGB channels continue to negatively impact segmentation accuracy when errors in colorization occur. Despite this, previous studies have not rigorously quantified the effects of erroneous colorization on segmentation performance. In this paper, we propose a novel statistical approach to evaluate the impact of inaccurate RGB information on image-based point cloud segmentation. We categorize RGB inaccuracies into two types: incorrect color information and similar color information. Our results demonstrate that both types of color inaccuracies significantly degrade segmentation accuracy, with similar color errors particularly affecting the extraction of geometric features. These findings highlight the critical need to reassess the role of RGB information in point cloud segmentation and its implications for future algorithm design.
AB - Point cloud semantic segmentation, the process of classifying each point into predefined categories, is essential for 3D scene understanding. While image-based segmentation is widely adopted due to its maturity, methods relying solely on RGB information often suffer from degraded performance due to color inaccuracies. Recent advancements have incorporated additional features such as intensity and geometric information, yet RGB channels continue to negatively impact segmentation accuracy when errors in colorization occur. Despite this, previous studies have not rigorously quantified the effects of erroneous colorization on segmentation performance. In this paper, we propose a novel statistical approach to evaluate the impact of inaccurate RGB information on image-based point cloud segmentation. We categorize RGB inaccuracies into two types: incorrect color information and similar color information. Our results demonstrate that both types of color inaccuracies significantly degrade segmentation accuracy, with similar color errors particularly affecting the extraction of geometric features. These findings highlight the critical need to reassess the role of RGB information in point cloud segmentation and its implications for future algorithm design.
KW - colorization
KW - point cloud
KW - semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=105004662981&partnerID=8YFLogxK
U2 - 10.1109/ICVISP64524.2024.10959389
DO - 10.1109/ICVISP64524.2024.10959389
M3 - Conference Proceeding
AN - SCOPUS:105004662981
T3 - 2024 IEEE 8th International Conference on Vision, Image and Signal Processing, ICVISP 2024
BT - 2024 IEEE 8th International Conference on Vision, Image and Signal Processing, ICVISP 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th IEEE International Conference on Vision, Image and Signal Processing, ICVISP 2024
Y2 - 27 December 2024 through 29 December 2024
ER -