SimLOG : Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds

Mingqiang WEI, Baian CHEN, Liangliang NAN, Haoran XIE, Lipeng GU, Dening LU, Fu Lee WANG, Qing LI

Research output: Journal PublicationsJournal Article (refereed)peer-review

Abstract

The acquisition of both local and global features from irregular point clouds is crucial for 3D object detection (3DOD). Current mainstream 3D detectors neglect significant local features during pooling operations or disregard many global features of the overall scene context. This paper proposes new techniques for simultaneously learning local-global features of scene point clouds to enhance 3DOD. Specifically, we propose an efficient 3DOD network in indoor point clouds, named SimLOG, which utilizes simultaneous local-global feature learning. SimLOG has two main contributions: a Dynamic Points Interaction (DPI) module to recover local features lost during pooling, and a Global Context Aggregation(GCA) module to aggregate multi-scale features from various layers of the encoder to improve scene context awareness. Unlike traditional local-global feature learning methods, our DPI and GCA modules are integrated into a single feature learning module, making it easily detachable and able to be incorporated into existing 3DOD networks to enhance their performance. SimLOG demonstrates superior performance over twenty competitors in terms of detection accuracy and robustness on both the SUN RGB-D and ScanNet V2 datasets. Specifically, SimLOG boosts the baseline VoteNet by 8.1% of [email protected] on ScanNet V2 and by 3.9% of [email protected] on SUN RGB-D. Code is publicly available at https://github.com/chenbaian-cs/SimLOG.
Original languageEnglish
Pages (from-to)1-14
JournalIEEE Transactions on Intelligent Transportation Systems
DOIs
Publication statusE-pub ahead of print - 5 Sept 2024

Fingerprint

Dive into the research topics of 'SimLOG : Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds'. Together they form a unique fingerprint.

Cite this