Distortion-Aware Monocular Depth Estimation for Omnidirectional Images

Hong Xiang Chen, Kunhong Li, Zhiheng Fu, Mengyi Liu, Zonghao Chen, Yulan Guo

Research output: Contribution to journalArticlepeer-review

18 Citations (Web of Science)


Image distortion is a main challenge for tasks on panoramas. In this work, we propose a Distortion-Aware Monocular Omnidirectional (DAMO) network to estimate dense depth maps from indoor panoramas. First, we introduce a distortion-aware module to extract semantic features from omnidirectional images. Specifically, we exploit deformable convolution to adjust its sampling grids to geometric distortions on panoramas. We also utilize a strip pooling module to sample against horizontal distortion introduced by inverse gnomonic projection. Second, we introduce a plug-and-play spherical-aware weight matrix for our loss function to handle the uneven distribution of areas projected from a sphere. Experiments on the 360D dataset show that the proposed method can effectively extract semantic features from distorted panoramas and alleviate the supervision bias caused by distortion. It achieves the state-of-the-art performance on the 360D dataset with high efficiency.

Original languageEnglish
Article number9319252
Pages (from-to)334-338
Number of pages5
JournalIEEE Signal Processing Letters
Publication statusPublished - 2021


Dive into the research topics of 'Distortion-Aware Monocular Depth Estimation for Omnidirectional Images'. Together they form a unique fingerprint.

Cite this