Refining disparity maps using deep learning and edge-aware smoothing filter

Abd Gani, Shamsul Fakhar and Miskon, Muhammad Fahmi and Hamzah, Rostam Affendi and Hamid, Mohd Saad and Kadmin, Ahmad Fauzan and Herman, Adi Irwan (2024) Refining disparity maps using deep learning and edge-aware smoothing filter. Bulletin of Electrical Engineering and Informatics, 13 (3). pp. 1961-1969. ISSN 2089-3191

Text 0173809122024113730.pdf Available under License Creative Commons Attribution Share Alike. Download (1MB)

Abstract

Stereo matching algorithm is crucial for applications that rely on three-dimensional (3D) surface reconstruction, producing a disparity map that contains depth information by computing the disparity values between corresponding points from a stereo image pair. In order to yield desirable results, the proposed stereo matching algorithm must possess a high degree of resilience against radiometric variation and edge inconsistencies. In this article convolutional neural network (CNN) is employed in the first stage to generate the raw matching cost, which is subsequently filtered with a bilateral filter (BF) and applied with cross-based cost aggregation (CBCA) during the cost aggregation stage to enhance precision. Winner-take-all (WTA) strategy is implemented to normalise the disparity map values. Finally, the resulting output is subjected to an edge-aware smoothing filter (EASF) to reduce the noise. Due to its resistance to high contrast and brightness, the filter is found to be effective in refining and eliminating noise from the output image. Despite discontinuities like adiron's lost cup handle or artl's shattered rods, this approach, based on experimental research utilizing a Middlebury standard validation benchmark, yields a high level of accuracy, with an average non-occluded error of 6.79%, comparable to other published methods

Item Type:	Article
Uncontrolled Keywords:	Computer vision, Deep learning, Disparity map, Edge-aware filter, Stereo matching
Divisions:	Faculty of Electrical and Electronic Engineering Technology
Depositing User:	Norfaradilla Idayu Ab. Ghafar
Date Deposited:	08 Oct 2025 01:01
Last Modified:	08 Oct 2025 01:01
URI:	http://eprints.utem.edu.my/id/eprint/28995
Statistic Details:	View Download Statistic

Actions (login required)

View Item