Fast Depth Reconstruction Using Deep Convolutional Neural Networks

Maslov, Dmitrii; Makarov, Ilya

doi:10.1007/978-3-030-85030-2_38

Cited by 10 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Yin et al (2019) argued that most metrics neglect geometric constraints in the three-dimensional space, so they developed a loss that enforces geometrical constraints. Another alternative to pixel-wise metrics is perceptual loss ( Johnson, Alahi & Li, 2016 ), which was successfully used in many depth-related tasks ( Makarov, Aliev & Gerasimova, 2017 ; Makarov et al, 2017 ; Makarov, Korinevskaya & Aliev, 2018a ; Makarov & Korinevskaya, 2019 ; Makarov, Korinevskaya & Aliev, 2018b ; Makarov, Korinevskaya & Aliev, 2018c ; Makarov et al, 2019 ; Maslov & Makarov, 2021 ). To reduce blurring of estimated depths, a new model with fusion mechanisms was proposed by Hu et al (2019) .…”

Section: Related Workmentioning

confidence: 99%

Self-supervised recurrent depth estimation with attention mechanisms

Makarov

Bakhanova

Nikolenko

et al. 2022

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Depth estimation has been an essential task for many computer vision applications, especially in autonomous driving, where safety is paramount. Depth can be estimated not only with traditional supervised learning but also via a self-supervised approach that relies on camera motion and does not require ground truth depth maps. Recently, major improvements have been introduced to make self-supervised depth prediction more precise. However, most existing approaches still focus on single-frame depth estimation, even in the self-supervised setting. Since most methods can operate with frame sequences, we believe that the quality of current models can be significantly improved with the help of information about previous frames. In this work, we study different ways of integrating recurrent blocks and attention mechanisms into a common self-supervised depth estimation pipeline. We propose a set of modifications that utilize temporal information from previous frames and provide new neural network architectures for monocular depth estimation in a self-supervised manner. Our experiments on the KITTI dataset show that proposed modifications can be an effective tool for exploiting temporal information in a depth prediction pipeline.

show abstract