TY - CONF

T1 - Robust Regression for Monocular Depth Estimation

AU - Lienen, Julian

AU - Nommensen, Nils

AU - Ewerth, Ralph

AU - Hüllermeier, Eyke

N1 - This work was supported by the German Research Foundation (DFG) under Grant No. 420493178. Moreover, computational resources were provided by the Paderborn Center for Parallel Computing (PC2).

PY - 2021

Y1 - 2021

N2 - Learning accurate models for monocular depth estimation requires precise depth annotation as e.g. gathered through LiDAR scanners. Because the data acquisition with sensors of this kind is costly and does not scale well in general, less advanced depth sources, such as time-of-flight cameras, are often used instead. However, these sensors provide less reliable signals, resulting in imprecise depth data for training regression models. As shown in idealized environments, the noise produced by commonly used RGB-D sensors violates standard statistical assumptions of regression methods, such as least squares estimation. In this paper, we investigate whether robust regression methods, which are more tolerant toward violations of statistical assumptions, can mitigate the effects of low-quality data. As a viable alternative to established approaches of that kind, we propose the use of so-called superset learning, where the original data is replaced by (less precise but more reliable) set-valued data. To evaluate and compare the methods, we provide an extensive empirical study on common benchmark data for monocular depth estimation. Our results clearly show the superiority of robust variants over conventional regression.

AB - Learning accurate models for monocular depth estimation requires precise depth annotation as e.g. gathered through LiDAR scanners. Because the data acquisition with sensors of this kind is costly and does not scale well in general, less advanced depth sources, such as time-of-flight cameras, are often used instead. However, these sensors provide less reliable signals, resulting in imprecise depth data for training regression models. As shown in idealized environments, the noise produced by commonly used RGB-D sensors violates standard statistical assumptions of regression methods, such as least squares estimation. In this paper, we investigate whether robust regression methods, which are more tolerant toward violations of statistical assumptions, can mitigate the effects of low-quality data. As a viable alternative to established approaches of that kind, we propose the use of so-called superset learning, where the original data is replaced by (less precise but more reliable) set-valued data. To evaluate and compare the methods, we provide an extensive empirical study on common benchmark data for monocular depth estimation. Our results clearly show the superiority of robust variants over conventional regression.

KW - Robust regression

KW - data imprecisiation

KW - monocular depth estimation

KW - superset learning

UR - http://www.scopus.com/inward/record.url?scp=85159962970&partnerID=8YFLogxK

M3 - Paper

SP - 1001

EP - 1016

ER -