EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PCMTRefer: Symmetry-Aware Text-Guided Point Mamba for Referring Segmentation in Indoor 3D Point Clouds

Li Yuan, Bo Kong, Chenhao Li, Anting Guo, Wenjiang Huang

Symmetry · 03.08.2026 · 18 (8) · 1313

DOI: 10.3390/sym18081313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 03.08.2026. Verfasst von Li Yuan und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Indoor 3D referring segmentation aims to identify and segment the target object in a point cloud according to a natural language expression. Although recent advances in multimodal feature fusion have markedly improved this task, existing methods do not jointly model the structural regularities commonly observed in indoor objects, such as approximate symmetry and repetitive local patterns, in conjunction with the directional constraints conveyed by referring expressions. In this work, we formulate symmetry-aware representation as the extraction of direction-consistent structural responses from both forward and backward traversals of the same spatially ordered sequence while preserving direction-sensitive variations introduced by occlusion, point cloud incompleteness, and cluttered scene layouts. Based on this formulation, we propose PCMTRefer, a symmetry-aware text-guided Point Mamba framework for indoor 3D referring segmentation. The input point cloud is first partitioned using an octree and arranged into a spatially coherent sequence via Z-order (Morton) ordering. A bidirectional state-space encoder then aggregates complementary context from both traversal directions, yielding richer representations of regular boundaries, repetitive structures, and approximately bilateral object geometries. In parallel, an asymmetric text-to-point guidance module injects semantic cues—object categories, attributes, and spatial relationships—into point-wise features, while a Background-Relaxation Token offers an auxiliary matching channel for non-target background regions. A Gumbel-Softmax-based semantic primitive learning module further extracts discriminative cues from referring expressions and integrates language semantics with point-level geometric features through a multi-scale decoder. Experimental results on the ScanRefer benchmark show that PCMTRefer achieves an Overall Acc@0.25 of 58.56%, an Overall Acc@0.5 of 54.19%, and an mIoU of 49.97%. Multi-seed validation further confirms the statistical stability of these results, with standard deviations of less than 0.2% across three independent runs.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yuan, L., Kong, B., Li, C., Guo, A., & Huang, W. (2026). PCMTRefer: Symmetry-Aware Text-Guided Point Mamba for Referring Segmentation in Indoor 3D Point Clouds. Symmetry, 18(8), 1313. https://doi.org/10.3390/sym18081313

Vancouver

Yuan L, Kong B, Li C, Guo A, Huang W. PCMTRefer: Symmetry-Aware Text-Guided Point Mamba for Referring Segmentation in Indoor 3D Point Clouds. Symmetry. 2026;18(8):1313. doi:10.3390/sym18081313

BibTeX
@article{Yuan2026,
  author = {Yuan, Li and Kong, Bo and Li, Chenhao and Guo, Anting and Huang, Wenjiang},
  title = {PCMTRefer: Symmetry-Aware Text-Guided Point Mamba for Referring Segmentation in Indoor 3D Point Clouds},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1313},
  doi = {10.3390/sym18081313}
}
Kostenlos starten →