Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Simple Yet Effective Way for Improving the Performance of Depth Map Super-Resolution

Authors
Yeo, Yoon-JaeSagong, Min-CheolShin, Yong-GooJung, Seung-WonKo, Sung-Jea
Issue Date
2020
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Image color analysis; Color; Convolution; Feature extraction; PSNR; Image edge detection; Standards; Depth map super-resolution (SR); convolutional neural network; deep learning
Citation
IEEE SIGNAL PROCESSING LETTERS, v.27, pp.2099 - 2103
Indexed
SCIE
SCOPUS
Journal Title
IEEE SIGNAL PROCESSING LETTERS
Volume
27
Start Page
2099
End Page
2103
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/59100
DOI
10.1109/LSP.2020.3039429
ISSN
1070-9908
Abstract
In depth map super-resolution (SR), a high-resolution color image plays an important role as guidance for preventing blurry depth boundaries. However, excessive/deficient use of the color image features often causes performance degradation such as texture-copying/edge-smoothing in flat/boundary areas. To alleviate these problems, this letter presents a simple yet effective method for enhancing the performance of the SR without requiring significant modifications to the original SR network. To this end, we present a self-selective concatenation (SSC), which is a substitute for the conventional feature concatenation. In the upsampling layers of the SR network, the SSC extracts spatial and channel attention from both color and depth features such that color features can be selectively used for depth SR. Specifically, the SSC learns to use sufficient color features for rendering sharp depth boundaries, whereas their effects are reduced in smooth regions to prevent texture-copying. The proposed SSC can be included in any existing SR networks that have the encoder-decoder structure. The experimental results show that the proposed method can further improve the performances of existing SR networks in terms of the root mean squared error and peak signal-to-noise ratio.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Jung, Seung won photo

Jung, Seung won
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE