Revisiting 360 Depth Estimation With PanoGabor: A New Fusion Perspective
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-05 · 48 (5) · 5979-5991
DOI: 10.1109/tpami.2026.3653796 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-05. Verfasst von Zhijie Shen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Depth estimation from a monocular 360 image is important to the perception of the entire 3D environment. However, the inherent distortion and large field of view (FoV) in 360 images pose great challenges for this task. To this end, existing mainstream solutions typically introduce additional perspective-based 360 representations (e.g., Cubemap) to achieve effective feature extraction. Nevertheless, regardless of the introduced representations, they eventually need to be unified into the equirectangular projection (ERP) format for the subsequent depth estimation, which inevitably reintroduces additional distortions. In this work, we propose an oriented-distortion-aware Gabor Fusion framework (PGFuse) to address the above challenges. First, we introduce Gabor filters that analyze texture in the frequency domain, extending the receptive fields and enhancing depth cues. To address the reintroduced distortions, we design a latitude-aware distortion representation to generate customized, distortion-aware Gabor filters (PanoGabor filters). Furthermore, we design a channel-wise and spatial-wise unidirectional fusion module (CS-UFM) that integrates the proposed PanoGabor filters to unify other representations into the ERP format, delivering effective and distortion-aware features. Considering the orientation sensitivity of the Gabor transform, we further introduce a spherical gradient constraint to stabilize this sensitivity. Experimental results on three popular indoor 360 benchmarks demonstrate the superiority of the proposed PGFuse to existing state-of-the-art solutions. Code and models will be available at https://github.com/zhijieshen-bjtu/PGFuse.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Shen, Z., Lin, C., Nie, L., Liao, K., Lin, W., & Zhao, Y. (2026). Revisiting 360 Depth Estimation With PanoGabor: A New Fusion Perspective. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(5), 5979-5991. https://doi.org/10.1109/tpami.2026.3653796
Vancouver
Shen Z, Lin C, Nie L, Liao K, Lin W, Zhao Y. Revisiting 360 Depth Estimation With PanoGabor: A New Fusion Perspective. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(5):5979-5991. doi:10.1109/tpami.2026.3653796
BibTeX
@article{Shen2026,
author = {Shen, Zhijie and Lin, Chunyu and Nie, Lang and Liao, Kang and Lin, Weisi and Zhao, Yao},
title = {Revisiting 360 Depth Estimation With PanoGabor: A New Fusion Perspective},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {5},
pages = {5979--5991},
doi = {10.1109/tpami.2026.3653796}
}
EUVIMED