CurrI2P: inter- and intra-modality similarity curriculum learning for image-to-point cloud registration
The Visual Computer · 2025-09 · 41 (11) · 8645-8658
DOI: 10.1007/s00371-025-03889-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Visual Computer, online erschienen am 07.04.2025. Verfasst von Liwei Lin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Image-to-point cloud (I2P) registration aims to align 2D images and 3D point clouds within the same scene. However, existing methods neglect the differences in learning difficulties among different samples, failing to bridge the image-to-point cloud modality gap adequately. Moreover, the features of images or point clouds within the same modality are easily affected by various geometric transformations, which further increases the complexity of the registration task. To address these issues, we propose a similarity curriculum learning framework for I2P registration, termed CurrI2P, which not only effectively captures similarities between different data pairs but also gradually adapts the model to more complex data transformations. Specifically, we first present inter-modality similarity curriculum learning to progressively enhance cross-modality similarity to reduce inaccurate matches caused by coarse registration at the early training stage. In addition, we design intra-modality similarity curriculum learning, particularly targeting to learn invariant features of images or point clouds within the same modality under the geometric disturbance of increasing magnitude. In experiments, we incorporate CurrI2P into different baselines to validate the feasibility and achieve state-of-the-art performance on both KITTI and nuScenes datasets. The code is available at https://github.com/lin-liwei/CurrI2P.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Lin, L., Lin, C., Nie, L., Huang, S., & Zhao, Y. (2025). CurrI2P: inter- and intra-modality similarity curriculum learning for image-to-point cloud registration. The Visual Computer, 41(11), 8645-8658. https://doi.org/10.1007/s00371-025-03889-7
Vancouver
Lin L, Lin C, Nie L, Huang S, Zhao Y. CurrI2P: inter- and intra-modality similarity curriculum learning for image-to-point cloud registration. The Visual Computer. 2025;41(11):8645-8658. doi:10.1007/s00371-025-03889-7
BibTeX
@article{Lin2025,
author = {Lin, Liwei and Lin, Chunyu and Nie, Lang and Huang, Shujuan and Zhao, Yao},
title = {CurrI2P: inter- and intra-modality similarity curriculum learning for image-to-point cloud registration},
journal = {The Visual Computer},
year = {2025},
volume = {41},
number = {11},
pages = {8645--8658},
doi = {10.1007/s00371-025-03889-7}
}
EUVIMED