UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Xing, Huang, Jinyang, Cui, Feng-Qi, Tong, Anyang, Wang, Ruimin, Liu, Liu, Guo, Dan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912862152163328
author Yi, Xing
Huang, Jinyang
Cui, Feng-Qi
Tong, Anyang
Wang, Ruimin
Liu, Liu
Guo, Dan
author_facet Yi, Xing
Huang, Jinyang
Cui, Feng-Qi
Tong, Anyang
Wang, Ruimin
Liu, Liu
Guo, Dan
contents The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple datasets, they fail to model geometric relationships in sparse point cloud scenes and ignore the feature distribution in significant areas, which ultimately restricts their performance. To deal with this issue, a unified 3D indoor detection framework, called UniGeo, is proposed. To model geometric relations in scenes, we first propose a geometry-aware learning module that establishes a learnable mapping from spatial relationships to feature weights, which enabes explicit geometric feature enhancement. Then, to further enhance point cloud feature representation, we propose a dynamic channel gating mechanism that leverages learnable channel-wise weighting. This mechanism adaptively optimizes features generated by the sparse 3D U-Net network, significantly enhancing key geometric information. Extensive experiments on six different indoor scene datasets clearly validate the superior performance of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22616
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating
Yi, Xing
Huang, Jinyang
Cui, Feng-Qi
Tong, Anyang
Wang, Ruimin
Liu, Liu
Guo, Dan
Computer Vision and Pattern Recognition
The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple datasets, they fail to model geometric relationships in sparse point cloud scenes and ignore the feature distribution in significant areas, which ultimately restricts their performance. To deal with this issue, a unified 3D indoor detection framework, called UniGeo, is proposed. To model geometric relations in scenes, we first propose a geometry-aware learning module that establishes a learnable mapping from spatial relationships to feature weights, which enabes explicit geometric feature enhancement. Then, to further enhance point cloud feature representation, we propose a dynamic channel gating mechanism that leverages learnable channel-wise weighting. This mechanism adaptively optimizes features generated by the sparse 3D U-Net network, significantly enhancing key geometric information. Extensive experiments on six different indoor scene datasets clearly validate the superior performance of our method.
title UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.22616