Fitness of General-Purpose Monocular Depth Estimation Architectures for Transparent Structures
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Due to material properties, monocular depth estimation of transparent structures is inherently challenging. Recent advances leverage additional knowledge that is not available in all contexts, i.e., known shape or depth information from a sensor. General-purpose machine learning models, that do not utilize such additional knowledge, have not yet been explicitly evaluated regarding their performance on transparent structures. In this work, we show that these models show poor performance on the depth estimation of transparent structures. However, fine-tuning on suitable data sets, such as ClearGrasp, increases their estimation performance on the task at hand. Our evaluations show that high performance on general-purpose benchmarks translates well into performance on transparent objects after fine-tuning. Furthermore, our analysis suggests, that state-of-theart high-performing models are not able to capture a high grade of detail from both the image foreground and background at the same time. This finding shows the demand for a combination of existing models to further enhance depth estimation quality.
Description
CCS Concepts: Computing methodologies --> Computer vision; Shape inference
@inproceedings{10.2312:egs.20221020,
booktitle = {Eurographics 2022 - Short Papers},
editor = {Pelechano, Nuria and Vanderhaeghe, David},
title = {{Fitness of General-Purpose Monocular Depth Estimation Architectures for Transparent Structures}},
author = {Wirth, Tristan and Jamili, Aria and Buelow, Max von and Knauthe, Volker and Guthe, Stefan},
year = {2022},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-169-4},
DOI = {10.2312/egs.20221020}
}