3D Geometric Shape Assembly via Efficient Point Cloud Matching
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911955596345344 |
|---|---|
| author | Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu |
| author_facet | Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu |
| contents | Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3D Geometric Shape Assembly via Efficient Point Cloud Matching Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu Computer Vision and Pattern Recognition Artificial Intelligence Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr. |
| title | 3D Geometric Shape Assembly via Efficient Point Cloud Matching |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.10542 |