Multi-scale Monocular Panorama Depth Estimation
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Panorama images are widely used for scene depth estimation as they provide comprehensive scene representation. The existing deep-learning monocular panorama depth estimation networks produce inconsistent, discontinuous, and poor-quality depth maps. To overcome this, we propose a novel multi-scale monocular panorama depth estimation framework. We use a coarseto- fine depth estimation approach, where multi-scale tangent perspective images, projected from 360 images, are given to coarse and fine encoder-decoder networks to produce multi-scale perspective depth maps, that are merged to get low and high-resolution 360 depth maps. The coarse branch extracts holistic features that guide fine branch extracted features using a Multi-Scale Feature Fusion (MSFF) module at the network bottleneck. The performed experiments on the Stanford2D3D benchmark dataset show that our model outperforms the existing methods, producing consistent, smooth, structure-detailed, and accurate depth maps.
Description
CCS Concepts: Computing methodologies -> Scene understanding
@inproceedings{10.2312:pg.20231282,
booktitle = {Pacific Graphics Short Papers and Posters},
editor = {Chaine, Raphaëlle and Deng, Zhigang and Kim, Min H.},
title = {{Multi-scale Monocular Panorama Depth Estimation}},
author = {Mohadikar, Payal and Fan, Chuanmao and Zhao, Chenxi and Duan, Ye},
year = {2023},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-234-9},
DOI = {10.2312/pg.20231282}
}