Mean-Variance Loss for Monocular Depth Estimation
Lists
Only you see this
Abstract
Monocular depth estimation is a widely studied computer vision problem with a vast variety of applications. In this paper, we formulate it as a pixel-wise classification task and use a mean-variance loss for robust depth estimation via distribution learning. More precisely, the mean-variance loss is composed of a mean loss that penalizes the difference between the mean of predicted depth distribution and the ground-truth depth, and a variance loss that penalizes the variance of predicted depth distribution to obtain a more focused distribution. The mean-variance loss is jointly trained with the soft-max loss to supervise a Deep Convolutional Neural Networks (DCNN) for depth estimation. Experimental results on the NYUDv2 dataset show that the proposed method outperforms previous state-of-the-art approaches.
BibTeX
@inproceedings{zou2019mean,
author = {Hongwei Zou and Ke Xian and Jiaqi Yang and Zhiguo Cao},
title = {{Mean-Variance Loss for Monocular Depth Estimation}},
booktitle = {ICIP},
year = {2019},
doi = {10.1109/icip.2019.8803170},
}Loading related content...