Robust-DefReg: a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paper
Point cloud registration is a critical process in computer vision and measurement science, aimed at determining transformations between corresponding sets of points for accurate spatial alignment. In particular, non-rigid registration involves estimating flexible transformations that map a source po...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
2025
|
| In: |
Measurement science and technology
Year: 2025, Jahrgang: 36, Heft: 1, Pages: ? |
| ISSN: | 1361-6501 |
| DOI: | 10.1088/1361-6501/ad916c |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1088/1361-6501/ad916c Verlag, lizenzpflichtig, Volltext: https://dx.doi.org/10.1088/1361-6501/ad916c 
|
| Verfasserangaben: | Sara Monji-Azad, Marvin Kinz, David Männel, Claudia Scherl and Jürgen Hesser |
MARC
| LEADER | 00000caa a22000002c 4500 | ||
|---|---|---|---|
| 001 | 193218192X | ||
| 003 | DE-627 | ||
| 005 | 20251106154255.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 250731s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6501/ad916c |2 doi | |
| 035 | |a (DE-627)193218192X | ||
| 035 | |a (DE-599)KXP193218192X | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Monji Azad, Sara |d 1986- |e VerfasserIn |0 (DE-588)1283596660 |0 (DE-627)1839374969 |4 aut | |
| 245 | 1 | 0 | |a Robust-DefReg |b a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paper |c Sara Monji-Azad, Marvin Kinz, David Männel, Claudia Scherl and Jürgen Hesser |
| 264 | 1 | |c 2025 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a In der Verantwortlichkeitsangabe ist der dritte Autor fälschlich als Männel angegeben | ||
| 500 | |a Online veröffentlicht: 25. November 2024 | ||
| 500 | |a Gesehen am 31.07.2025 | ||
| 520 | |a Point cloud registration is a critical process in computer vision and measurement science, aimed at determining transformations between corresponding sets of points for accurate spatial alignment. In particular, non-rigid registration involves estimating flexible transformations that map a source point cloud to a target point cloud, even under conditions of stretching, compression, or other complex deformations. This task becomes especially challenging when addressing measurement-specific issues like varying degrees of deformation, noise, and outliers, all of which can impact measurement accuracy and reliability. This paper introduces Robust-DefReg, a novel method for non-rigid point cloud registration that applies graph convolutional networks (GCNNs) within a coarse-to-fine registration framework. This end-to-end pipeline harnesses global feature learning to establish robust correspondences and precise transformations, enabling high accuracy across different deformation scales and noise levels. A key contribution of Robust-DefReg is its demonstrated resilience to various challenges, such as substantial deformations, noise, and outliers, factors often underreported in existing registration literature. In addition, we present SynBench, a comprehensive benchmark dataset specifically designed for evaluating non-rigid point cloud registration in realistic measurement scenarios. Unlike previous datasets, SynBench incorporates a range of challenges, making it a valuable tool for the fair assessment of registration methods in measurement applications. Experimental results on SynBench and additional datasets show that Robust-DefReg consistently outperforms state-of-the-art methods, offering higher registration accuracy and robustness, even with up to 45% outliers. SynBench and the Robust-DefReg source code are publicly accessible for further research and development at https://doi.org/10.11588/data/R9IKCF and https://github.com/m-kinz/Robust-DefReg, respectively. | ||
| 700 | 1 | |a Kinz, Marvin |d 1998- |e VerfasserIn |0 (DE-588)1310791422 |0 (DE-627)1870898214 |4 aut | |
| 700 | 1 | |a Männle, David |d 1988- |e VerfasserIn |0 (DE-588)1124103198 |0 (DE-627)87782603X |0 (DE-576)48230300X |4 aut | |
| 700 | 1 | |a Scherl, Claudia |d 1977- |e VerfasserIn |0 (DE-588)132069555 |0 (DE-627)517465426 |0 (DE-576)298927101 |4 aut | |
| 700 | 1 | |a Hesser, Jürgen |d 1964- |e VerfasserIn |0 (DE-588)1020647353 |0 (DE-627)691291071 |0 (DE-576)361513739 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Measurement science and technology |d Bristol : IOP Publ., 1990 |g 36(2025), 1, Artikel-ID 015426, Seite ? |h Online-Ressource |w (DE-627)225274744 |w (DE-600)1362523-8 |w (DE-576)077608003 |x 1361-6501 |7 nnas |a Robust-DefReg a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paper |
| 773 | 1 | 8 | |g volume:36 |g year:2025 |g number:1 |g elocationid:015426 |g pages:? |a Robust-DefReg a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paper |
| 856 | 4 | 0 | |u https://doi.org/10.1088/1361-6501/ad916c |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1088/1361-6501/ad916c |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20250731 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1020647353 |a Hesser, Jürgen |m 1020647353:Hesser, Jürgen |d 60000 |d 65200 |d 60000 |e 60000PH1020647353 |e 65200PH1020647353 |e 60000PH1020647353 |k 0/60000/ |k 1/60000/65200/ |k 0/60000/ |p 5 |y j | ||
| 998 | |g 132069555 |a Scherl, Claudia |m 132069555:Scherl, Claudia |d 60000 |d 62100 |e 60000PS132069555 |e 62100PS132069555 |k 0/60000/ |k 1/60000/62100/ |p 4 | ||
| 998 | |g 1124103198 |a Männle, David |m 1124103198:Männle, David |d 60000 |d 62100 |e 60000PM1124103198 |e 62100PM1124103198 |k 0/60000/ |k 1/60000/62100/ |p 3 | ||
| 998 | |g 1310791422 |a Kinz, Marvin |m 1310791422:Kinz, Marvin |d 130000 |e 130000PK1310791422 |k 0/130000/ |p 2 | ||
| 998 | |g 1283596660 |a Monji Azad, Sara |m 1283596660:Monji Azad, Sara |d 60000 |d 65200 |e 60000PM1283596660 |e 65200PM1283596660 |k 0/60000/ |k 1/60000/65200/ |p 1 |x j | ||
| 999 | |a KXP-PPN193218192X |e 4751142445 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"person":[{"display":"Monji Azad, Sara","family":"Monji Azad","given":"Sara","role":"aut"},{"given":"Marvin","role":"aut","family":"Kinz","display":"Kinz, Marvin"},{"role":"aut","given":"David","family":"Männle","display":"Männle, David"},{"given":"Claudia","role":"aut","family":"Scherl","display":"Scherl, Claudia"},{"given":"Jürgen","role":"aut","family":"Hesser","display":"Hesser, Jürgen"}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"2025"}],"note":["In der Verantwortlichkeitsangabe ist der dritte Autor fälschlich als Männel angegeben","Online veröffentlicht: 25. November 2024","Gesehen am 31.07.2025"],"title":[{"title":"Robust-DefReg","subtitle":"a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paper","title_sort":"Robust-DefReg"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"name":{"displayForm":["Sara Monji-Azad, Marvin Kinz, David Männel, Claudia Scherl and Jürgen Hesser"]},"recId":"193218192X","id":{"doi":["10.1088/1361-6501/ad916c"],"eki":["193218192X"]},"relHost":[{"id":{"issn":["1361-6501"],"eki":["225274744"],"zdb":["1362523-8"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"225274744","pubHistory":["1.1990 -"],"part":{"volume":"36","text":"36(2025), 1, Artikel-ID 015426, Seite ?","pages":"?","issue":"1","year":"2025"},"note":["Gesehen am 02.12.20"],"origin":[{"dateIssuedKey":"1990","publisher":"IOP Publ.","publisherPlace":"Bristol","dateIssuedDisp":"1990-"}],"title":[{"title":"Measurement science and technology","subtitle":"devoted to the theory, practice and application of measurement in physics, chemistry, engineering and the environmental and life sciences from inception to commercial exploitation","title_sort":"Measurement science and technology"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"disp":"Robust-DefReg a robust coarse to fine non-rigid point cloud registration method based on graph convolutional neural networks : paperMeasurement science and technology"}]} | ||
| SRT | |a MONJIAZADSROBUSTDEFR2025 | ||