3D Geometric Shape Assembly via Efficient Point Cloud Matching

Nahyuk Lee, Juhong Min, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, Minsu Cho
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26856-26873, 2024.

Abstract

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 compute. 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

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lee24s, title = {3{D} Geometric Shape Assembly via Efficient Point Cloud Matching}, author = {Lee, Nahyuk and Min, Juhong and Lee, Junha and Kim, Seungwook and Lee, Kanghee and Park, Jaesik and Cho, Minsu}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {26856--26873}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lee24s/lee24s.pdf}, url = {https://proceedings.mlr.press/v235/lee24s.html}, abstract = {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 compute. 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} }
Endnote
%0 Conference Paper %T 3D Geometric Shape Assembly via Efficient Point Cloud Matching %A Nahyuk Lee %A Juhong Min %A Junha Lee %A Seungwook Kim %A Kanghee Lee %A Jaesik Park %A Minsu Cho %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lee24s %I PMLR %P 26856--26873 %U https://proceedings.mlr.press/v235/lee24s.html %V 235 %X 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 compute. 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
APA
Lee, N., Min, J., Lee, J., Kim, S., Lee, K., Park, J. & Cho, M.. (2024). 3D Geometric Shape Assembly via Efficient Point Cloud Matching. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:26856-26873 Available from https://proceedings.mlr.press/v235/lee24s.html.

Related Material