SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918045757210624 |
|---|---|
| author | Monji-Azad, Sara Kinz, Marvin Scherl, Claudia Männle, David Hesser, Jürgen Löw, Nikolas |
| author_facet | Monji-Azad, Sara Kinz, Marvin Scherl, Claudia Männle, David Hesser, Jürgen Löw, Nikolas |
| contents | Non-rigid point cloud registration is a crucial task in computer vision. Evaluating a non-rigid point cloud registration method requires a dataset with challenges such as large deformation levels, noise, outliers, and incompleteness. Despite the existence of several datasets for deformable point cloud registration, the absence of a comprehensive benchmark with all challenges makes it difficult to achieve fair evaluations among different methods. This paper introduces SynBench, a new non-rigid point cloud registration dataset created using SimTool, a toolset for soft body simulation in Flex and Unreal Engine. SynBench provides the ground truth of corresponding points between two point sets and encompasses key registration challenges, including varying levels of deformation, noise, outliers, and incompleteness. To the best of the authors' knowledge, compared to existing datasets, SynBench possesses three particular characteristics: (1) it is the first benchmark that provides various challenges for non-rigid point cloud registration, (2) SynBench encompasses challenges of varying difficulty levels, and (3) it includes ground truth corresponding points both before and after deformation. The authors believe that SynBench enables future non-rigid point cloud registration methods to present a fair comparison of their achievements. SynBench is publicly available at: https://doi.org/10.11588/data/R9IKCF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14474 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration Monji-Azad, Sara Kinz, Marvin Scherl, Claudia Männle, David Hesser, Jürgen Löw, Nikolas Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Non-rigid point cloud registration is a crucial task in computer vision. Evaluating a non-rigid point cloud registration method requires a dataset with challenges such as large deformation levels, noise, outliers, and incompleteness. Despite the existence of several datasets for deformable point cloud registration, the absence of a comprehensive benchmark with all challenges makes it difficult to achieve fair evaluations among different methods. This paper introduces SynBench, a new non-rigid point cloud registration dataset created using SimTool, a toolset for soft body simulation in Flex and Unreal Engine. SynBench provides the ground truth of corresponding points between two point sets and encompasses key registration challenges, including varying levels of deformation, noise, outliers, and incompleteness. To the best of the authors' knowledge, compared to existing datasets, SynBench possesses three particular characteristics: (1) it is the first benchmark that provides various challenges for non-rigid point cloud registration, (2) SynBench encompasses challenges of varying difficulty levels, and (3) it includes ground truth corresponding points both before and after deformation. The authors believe that SynBench enables future non-rigid point cloud registration methods to present a fair comparison of their achievements. SynBench is publicly available at: https://doi.org/10.11588/data/R9IKCF. |
| title | SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning |
| url | https://arxiv.org/abs/2409.14474 |