Sorry, you need to enable JavaScript to visit this website.

On Regression Losses for Depth Estimation

Citation Author(s):
Marcela Carvalho, Bertrand Le Saux, Pauline Trouvé-Peloux, Andrés Almansa, Frédéric Champagnat
Submitted by:
Marcela Carvalho
Last updated:
9 October 2018 - 7:18am
Document Type:
Poster
Document Year:
2018
Event:
Presenters Name:
Marcela Carvalho
Paper Code:
1083

Abstract 

Abstract: 

Depth estimation from a single monocular image has reached great performances thanks to recent works based on deep networks. However, as various choices of losses, architectures and experimental conditions are proposed in the literature, it is difficult to establish their respective influence on the performances. In this paper we propose an in-depth study of various losses and experimental conditions for depth regression, on \nyu dataset. From this study we propose a new network for depth estimation combining an encoder-decoder architecture with an adversarial loss. This network reaches top scores in the competitive evaluation of NUYv2 dataset while being simpler to train in a single phase.

up
0 users have voted:

Dataset Files

icip2018_id1083.pdf

(256)