Mechanical Sciences
Mechanical Sciences
Mechanical Sciences
Articles | Volume 17, issue 1
Articles | Volume 17, issue 1
https://doi.org/10.5194/ms-17-221-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/ms-17-221-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 17, issue 1
Research article
 | 
11 Mar 2026
Research article |  | 11 Mar 2026

GAPS: Group-wise Affine-Perturbed Serialization for efficient 3D semantic segmentation

Yubin Tang, Yangchen Liu, and Zichuan Fan

Viewed

Total article views: 230 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
184 35 11 230 5 5
  • HTML: 184
  • PDF: 35
  • XML: 11
  • Total: 230
  • BibTeX: 5
  • EndNote: 5
Views and downloads (calculated since 11 Mar 2026)
Cumulative views and downloads (calculated since 11 Mar 2026)

Viewed (geographical distribution)

Total article views: 249 (including HTML, PDF, and XML) Thereof 249 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 04 Apr 2026
Download
Short summary
Current methods for analyzing three-dimensional points often fail to capture complex shapes because they scan in fixed directions. We introduce Group-wise Affine-Perturbed Serialization to solve this. Our method scans data along diverse, angled paths simultaneously to better capture geometry. This approach outperforms existing technologies in terms of accuracy without adding computational delay. It enables computers to understand real-world environments more precisely and efficiently. 
Read more
Share