Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3082-3090
DOI: 10.1609/aaai.v38i4.28091 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Hongjie Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).
Abstract (Originalsprache)
This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation in faithful PatchMatch multi-view stereo (MVS). We observe that the heuristic depth hypothesis sampling modes employed by PatchMatch MVS solvers are insensitive to (i) the piece-wise smooth distribution of depths across the object surface and (ii) the implicit multi-modal distribution of depth prediction probabilities along the ray direction on the surface points. Accordingly, we develop DeformSampler to learn distribution-sensitive sample spaces to (i) propagate depths consistent with the scene's geometry across the object surface and (ii) fit a Laplace Mixture model that approaches the point-wise probabilities distribution of the actual depths along the ray direction. We integrate DeformSampler into a learnable PatchMatch MVS system to enhance depth estimation in challenging areas, such as piece-wise discontinuous surface boundaries and weakly-textured regions. Experimental results on DTU and Tanks & Temples datasets demonstrate its superior performance and generalization capabilities compared to state-of-the-art competitors. Code is available at https://github.com/Geo-Tell/DS-PMNet.
Zitieren
APA
Li, H., Guo, Y., Zheng, X., & Xiong, H. (2024). Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3082-3090. https://doi.org/10.1609/aaai.v38i4.28091
Vancouver
Li H, Guo Y, Zheng X, Xiong H. Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3082-3090. doi:10.1609/aaai.v38i4.28091
BibTeX
@article{Li2024,
author = {Li, Hongjie and Guo, Yao and Zheng, Xianwei and Xiong, Hanjiang},
title = {Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {3082--3090},
doi = {10.1609/aaai.v38i4.28091}
}
EUVIMED