TY - JOUR
T1 - SPU-IMR
T2 - 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
AU - Nie, Ziming
AU - Wu, Qiao
AU - Lv, Chenlei
AU - Quan, Siwen
AU - Qi, Zhaoshuai
AU - Wang, Muze
AU - Yang, Jiaqi
N1 - Publisher Copyright:
Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2025/4/11
Y1 - 2025/4/11
N2 - Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve upsampling by performing local interpolation between point clouds or in the feature space, then regressing the interpolated points to appropriate positions. By contrast, our proposed method treats point cloud upsampling as a global shape completion problem. Specifically, our method first divides the point cloud into multiple patches. Then, a masking operation is applied to remove some patches, leaving visible point cloud patches. Finally, our custom-designed neural network iterative completes the missing sections of the point cloud through the visible parts. During testing, by selecting different mask sequences, we can restore various complete patches. A sufficiently dense upsampled point cloud can be obtained by merging all the completed patches. We demonstrate the superior performance of our method through both quantitative and qualitative experiments, showing overall superiority against both existing self-supervised and supervised methods.
AB - Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve upsampling by performing local interpolation between point clouds or in the feature space, then regressing the interpolated points to appropriate positions. By contrast, our proposed method treats point cloud upsampling as a global shape completion problem. Specifically, our method first divides the point cloud into multiple patches. Then, a masking operation is applied to remove some patches, leaving visible point cloud patches. Finally, our custom-designed neural network iterative completes the missing sections of the point cloud through the visible parts. During testing, by selecting different mask sequences, we can restore various complete patches. A sufficiently dense upsampled point cloud can be obtained by merging all the completed patches. We demonstrate the superior performance of our method through both quantitative and qualitative experiments, showing overall superiority against both existing self-supervised and supervised methods.
UR - http://www.scopus.com/inward/record.url?scp=105003946896&partnerID=8YFLogxK
U2 - 10.1609/aaai.v39i6.32667
DO - 10.1609/aaai.v39i6.32667
M3 - 会议文章
AN - SCOPUS:105003946896
SN - 2159-5399
VL - 39
SP - 6236
EP - 6244
JO - Proceedings of the AAAI Conference on Artificial Intelligence
JF - Proceedings of the AAAI Conference on Artificial Intelligence
IS - 6
Y2 - 25 February 2025 through 4 March 2025
ER -