TY - GEN
T1 - SIRA-PCR
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
AU - Chen, Suyi
AU - Xu, Hao
AU - Li, Ru
AU - Liu, Guanghui
AU - Fu, Chi Wing
AU - Liu, Shuaicheng
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Point cloud registration is essential for many applications. However, existing real datasets require extremely tedious and costly annotations, yet may not provide accurate camera poses. For the synthetic datasets, they are mainly object-level, so the trained models may not generalize well to real scenes. We design SIRA-PCR, a new approach to 3D point cloud registration. First, we build a synthetic scene-level 3D registration dataset, specifically designed with physically-based and random strategies to arrange diverse objects. Second, we account for variations in different sensing mechanisms and layout placements, then formulate a sim-to-real adaptation framework with an adaptive re-sample module to simulate patterns in real point clouds. To our best knowledge, this is the first work that explores sim-to-real adaptation for point cloud registration. Extensive experiments show the SOTA performance of SIRA-PCR on widely-used indoor and out-door datasets. The code and dataset will be released on https://github.com/Chen-Suyi/SIRA-Pytorc.h
AB - Point cloud registration is essential for many applications. However, existing real datasets require extremely tedious and costly annotations, yet may not provide accurate camera poses. For the synthetic datasets, they are mainly object-level, so the trained models may not generalize well to real scenes. We design SIRA-PCR, a new approach to 3D point cloud registration. First, we build a synthetic scene-level 3D registration dataset, specifically designed with physically-based and random strategies to arrange diverse objects. Second, we account for variations in different sensing mechanisms and layout placements, then formulate a sim-to-real adaptation framework with an adaptive re-sample module to simulate patterns in real point clouds. To our best knowledge, this is the first work that explores sim-to-real adaptation for point cloud registration. Extensive experiments show the SOTA performance of SIRA-PCR on widely-used indoor and out-door datasets. The code and dataset will be released on https://github.com/Chen-Suyi/SIRA-Pytorc.h
UR - https://www.scopus.com/pages/publications/85180577513
U2 - 10.1109/ICCV51070.2023.01324
DO - 10.1109/ICCV51070.2023.01324
M3 - 会议稿件
AN - SCOPUS:85180577513
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 14348
EP - 14359
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 2 October 2023 through 6 October 2023
ER -