Intrinsic Phase-Preserving Networks for Depth Super Resolution
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 1210-1218
DOI: 10.1609/aaai.v38i2.27883 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xuanhong Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).
Abstract (Originalsprache)
Depth map super-resolution (DSR) plays an indispensable role in 3D vision. We discover an non-trivial spectral phenomenon: the components of high-resolution (HR) and low-resolution (LR) depth maps manifest the same intrinsic phase, and the spectral phase of RGB is a superset of them, which suggests that a phase-aware filter can assist in the precise use of RGB cues. Motivated by this, we propose an intrinsic phase-preserving DSR paradigm, named IPPNet, to fully exploit inter-modality collaboration in a mutually guided way. In a nutshell, a novel Phase-Preserving Filtering Module (PPFM) is developed to generate dynamic phase-aware filters according to the LR depth flow to filter out erroneous noisy components contained in RGB and then conduct depth enhancement via the modulation of the phase-preserved RGB signal. By stacking multiple PPFM blocks, the proposed IPPNet is capable of reaching a highly competitive restoration performance. Extensive experiments on various benchmark datasets, e.g., NYU v2, RGB-D-D, reach SOTA performance and also well demonstrate the validity of the proposed phase-preserving scheme. Code: https://github.com/neuralchen/IPPNet/.
Zitieren
APA
Chen, X., Wang, H., Chen, J., Feng, K., Liu, J., Wang, X., Zhang, W., & Ni, B. (2024). Intrinsic Phase-Preserving Networks for Depth Super Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1210-1218. https://doi.org/10.1609/aaai.v38i2.27883
Vancouver
Chen X, Wang H, Chen J, Feng K, Liu J, Wang X, et al. Intrinsic Phase-Preserving Networks for Depth Super Resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):1210-1218. doi:10.1609/aaai.v38i2.27883
BibTeX
@article{Chen2024,
author = {Chen, Xuanhong and Wang, Hang and Chen, Jialiang and Feng, Kairui and Liu, Jinfan and Wang, Xiaohang and Zhang, Weimin and Ni, Bingbing},
title = {Intrinsic Phase-Preserving Networks for Depth Super Resolution},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {2},
pages = {1210--1218},
doi = {10.1609/aaai.v38i2.27883}
}
EUVIMED