Mini V-Net: Depth Estimation from Single Indoor-Outdoor Images using Strided-CNN

Ahmed J. Afifi, Olaf Hellwich, Toufique Ahmed Soomro

2020

Abstract

Depth estimation plays a vital role in many computer vision tasks including scene understanding and reconstruction. However, it is an ill-posed problem when it comes to estimating the depth from a single view due to the ambiguity and the lack of cues and prior knowledge. Proposed solutions so far estimate blurry depth images with low resolutions. Recently, Convolutional Neural Network (CNN) has been applied successfully to solve different computer vision tasks such as classification, detection, and segmentation. In this paper, we present a simple fully-convolutional encoder-decoder CNN for estimating depth images from a single RGB image with the same image resolution. For robustness, we leverage a non-convex loss function which is robust to the outliers to optimize the network. Our results show that a light simple model trained using a robust loss function outperforms or achieves comparable results with other methods quantitatively and qualitatively and produces better depth information of the scenes with sharper objects’ boundaries. Our model predicts the depth information in one shot with the same input resolution and without any further post-processing steps.

Paper Citation

in Harvard Style

Afifi A., Hellwich O. and Soomro T. (2020). Mini V-Net: Depth Estimation from Single Indoor-Outdoor Images using Strided-CNN. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 205-214. DOI: 10.5220/0009356102050214

in Bibtex Style

@conference{visapp20,
author={Ahmed J. Afifi and Olaf Hellwich and Toufique Ahmed Soomro},
title={Mini V-Net: Depth Estimation from Single Indoor-Outdoor Images using Strided-CNN},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={205-214},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009356102050214},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Mini V-Net: Depth Estimation from Single Indoor-Outdoor Images using Strided-CNN
SN - 978-989-758-402-2
AU - Afifi A.
AU - Hellwich O.
AU - Soomro T.
PY - 2020
SP - 205
EP - 214
DO - 10.5220/0009356102050214
PB - SciTePress