NL-DSE: Non-Local Neural Network with Decoder-Squeeze-and-Excitation for Monocular Depth Estimation

Monocular Depth Estimation is a popular and challenging problem for many years. IR CNNs (Convolutional Neural Networks)-based method with encoder-decoder architecture is proposed and shows a reasonable result. In this paper, we propose a SE-Net-based module for the decoder part in the encoder-decode...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 4
Main Authors Tsai, Tsung-Han, Wan, Wei-Chung
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
Acoustics
CNNs
Convolutional neural networks
Decoding
Design methodology
encoder-decoder
Estimation
monocular depth estimation
Neural networks
SE-Net
Speech processing
up-sampling recalibration
Online AccessGet full text

Cover

More Information
Summary:Monocular Depth Estimation is a popular and challenging problem for many years. IR CNNs (Convolutional Neural Networks)-based method with encoder-decoder architecture is proposed and shows a reasonable result. In this paper, we propose a SE-Net-based module for the decoder part in the encoder-decoder architecture to improve the result. We proposed a DSE (Decoder-Squeeze-and-Excitation) module to deal with the whole up-sampling process globally for the decoder part. We also include the Non-local Network space attention method to design the Non-Local Decoder-Squeeze-and-Excitation (NL-DSE) module. The proposed NL-DSE module is installed and evaluated on the NYU Depth V2 dataset and achieves higher accuracy. Moreover, the design is independent of the encoder-decoder architecture and can be applied in the other encoder-decoder networks to have a more accurate network.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095633