SGNet: Salient Geometric Network for Point Cloud Registration

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00380045" target="_blank" >RIV/68407700:21230/24:00380045 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IROS58592.2024.10802262" target="_blank" >https://doi.org/10.1109/IROS58592.2024.10802262</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IROS58592.2024.10802262" target="_blank" >10.1109/IROS58592.2024.10802262</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SGNet: Salient Geometric Network for Point Cloud Registration

Popis výsledku v původním jazyce

Point Cloud Registration (PCR) is a critical and challenging task in computer vision and robotics. One of the primary diffculties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for effcient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder signifcantly improves registration recall by reducing ambiguity in patchlevel superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. We introduce an anchor node selection strategy to optimize this highorder transformer further. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify critical correspondences for successful registration. The experiments conducted on the 3DMatch/3DLoMatch and KITTI datasets demonstrate the effectiveness of our method.

Název v anglickém jazyce

SGNet: Salient Geometric Network for Point Cloud Registration

Popis výsledku anglicky

Point Cloud Registration (PCR) is a critical and challenging task in computer vision and robotics. One of the primary diffculties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for effcient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder signifcantly improves registration recall by reducing ambiguity in patchlevel superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. We introduce an anchor node selection strategy to optimize this highorder transformer further. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify critical correspondences for successful registration. The experiments conducted on the 3DMatch/3DLoMatch and KITTI datasets demonstrate the effectiveness of our method.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GM22-23183M" target="_blank" >GM22-23183M: Nová generace algoritmů pro řešení problémů geometrie kamer</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

ISBN

979-8-3503-7771-2

ISSN

2153-0858

e-ISSN

2153-0866

Počet stran výsledku

7

Strana od-do

3276-3282

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Abu Dhabi

Datum konání akce

14. 10. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001411890000353