LCD: Learned cross-domain descriptors for 2D-3D matching

56Citations
Citations of this article
97Readers
Mendeley users who have this article in their library.

Abstract

In this work, we present a novel method to learn a local crossdomain descriptor for 2D image and 3D point cloud matching. Our proposed method is a dual auto-encoder neural network that maps 2D and 3D input into a shared latent space representation. We show that such local cross-domain descriptors in the shared embedding are more discriminative than those obtained from individual training in 2D and 3D domains. To facilitate the training process, we built a new dataset by collecting ≈ 1.4 millions of 2D-3D correspondences with various lighting conditions and settings from publicly available RGB-D scenes. Our descriptor is evaluated in three main experiments: 2D-3D matching, cross-domain retrieval, and sparse-to-dense depth estimation. Experimental results confirm the robustness of our approach as well as its competitive performance not only in solving cross-domain tasks but also in being able to generalize to solve sole 2D and 3D tasks. Our dataset and code are released publicly at https://hkust-vgd.github.io/lcd.

Cite

CITATION STYLE

APA

Pham, Q. H., Uy, M. A., Hua, B. S., Nguyen, D. T., Roig, G., & Yeung, S. K. (2020). LCD: Learned cross-domain descriptors for 2D-3D matching. In AAAI 2020 - 34th AAAI Conference on Artificial Intelligence (pp. 11856–11864). AAAI press. https://doi.org/10.1609/aaai.v34i07.6859

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free