Back to articles
Proceedings Paper
Volume: 37 | Article ID: IQSP-240
Image
Building End-to-End Deblur Image Quality Evaluation Simulation for Hybrid-EVS-CIS Sensor Images
  DOI :  10.2352/EI.2025.37.9.IQSP-240  Published OnlineFebruary 2025
Abstract
Abstract

Event-based Vision Sensor (EVS) generates pixel-level and low-latency event data that is useful for reconstructing temporal components of images for deblurring. In this new application development, we need to know how EVS hardware parameters affect the natural motion scene image quality (IQ) to determine hardware specifications before starting design. To realize this approach, it is beneficial to build an End-to-End IQ simulation that runs from hardware simulations to natural motion scene IQ evaluation. Previously, we developed a Hybrid-EVS-CIS simulator to generate synthesized color rotation disk images and their event data fed into an image deblur block. Then image blurriness was evaluated by using the Blurred Edge Width metric (BEW). This paper proposes the extended IQ evaluation, which is an End-to-End IQ simulation for natural motion scenes. A simultaneous evaluation of blurriness and noise on images was verified by using Visual Information Fidelity and Detail Loss Metric. We also build a method to assess pixel-speed using BEW. Those IQ evaluation methods were the last pieces to realize End-to-End IQ simulation.

Subject Areas :
Views 7
Downloads 2
 articleview.views 7
 articleview.downloads 2
  Cite this article 

Daisuke Saito, Kamal Rana, Zhiyao Yang, Wei Zhang, Bo Mu, Eiichi Funatsu, "Building End-to-End Deblur Image Quality Evaluation Simulation for Hybrid-EVS-CIS Sensor Imagesin Electronic Imaging,  2025,  pp 240-1 - 240-7,  https://doi.org/10.2352/EI.2025.37.9.IQSP-240

 Copy citation
  Copyright statement 
Copyright © 2025, Society for Imaging Science and Technology
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA