Attention-based matching cost for disparity estimation from light fields

JunYao Weng; Chang Liu; XiaoJuan Deng; Jun Qiu

doi:10.1117/12.3036046

22 November 2024 Attention-based matching cost for disparity estimation from light fields

JunYao Weng, Chang Liu, XiaoJuan Deng, Jun Qiu

Author Affiliations +

Proceedings Volume 13239, Optoelectronic Imaging and Multimedia Technology XI; 132390Y (2024) https://doi.org/10.1117/12.3036046
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Conference Poster

Abstract

This paper presents a neural network designed for light field (LF) disparity estimation. We improve the network's capability to use spatial and geometric information from light field data by:1. Incorporating positional encoding;2. Adding edge attention mechanisms. The positional encoding aids in deciphering the 3D structure of scenes, which is crucial for accurate LF disparity estimation. Meanwhile, edge attention directs the network to prioritize edge details, enabling the construction of more precise disparity maps. Additionally, edge attention ensures global consistency in disparity estimates, particularly in areas with prominent object edges and limited texture, where it can minimize estimation uncertainty. The attention mechanism also selectively refines features from each view, further boosting the accuracy of disparity estimation. Experiments demonstrate our model's improved accuracy, underscoring the effectiveness of our approach in enhancing LF disparity estimation techniques. The proposed method not only enhances performance but also streamlines the network architecture, making it more scalable and suitable for diverse computer vision scenarios.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

JunYao Weng, Chang Liu, XiaoJuan Deng, and Jun Qiu "Attention-based matching cost for disparity estimation from light fields", Proc. SPIE 13239, Optoelectronic Imaging and Multimedia Technology XI, 132390Y (22 November 2024); https://doi.org/10.1117/12.3036046

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE