ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation

Chuanqing Zhuang, Zhengda Lu, Yiqun Wang, Jun Xiao, Ying Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Scopus citations

Abstract

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an ACDNet based on the adaptively combined dilated convolution to predict the dense depth map for a monocular panoramic image. Specifically, we combine the convolution kernels with different dilations to extend the receptive field in the equirectangular projection. Meanwhile, we introduce an adaptive channel-wise fusion module to summarize the feature maps and get diverse attention areas in the receptive field along the channels. Due to the utilization of channel-wise attention in constructing the adaptive channel-wise fusion module, the network can capture and leverage the cross-channel contextual information efficiently. Finally, we conduct depth estimation experiments on three datasets (both virtual and real-world) and the experimental results demonstrate that our proposed ACDNet substantially outperforms the current state-of-the-art (SOTA) methods.
Original languageEnglish (US)
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages3653-3661
Number of pages9
DOIs
StatePublished - Jun 28 2022

Fingerprint

Dive into the research topics of 'ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation'. Together they form a unique fingerprint.

Cite this