Rethinking Deblurring Strategies for 3D Reconstruction: Joint Optimization vs. Modular Approaches

Akash Malhotra, Akash Malhotra, Nacéra Seghouani, Ahmad Abu Saiid, Alaa Almatuwa, Koumudi Ganepola

2025

Abstract

In this paper, we present a comparison between joint optimization and modular frameworks for addressing deblurring in multiview 3D reconstruction. Casual captures, especially with handheld devices, often contain blurry images that degrade the quality of 3D reconstruction. Joint optimization frameworks tackle this issue by integrating deblurring and 3D reconstruction into a unified learning process, leveraging information from overlapping blurry images. While effective, these methods increase the complexity and training time. Conversely, modular approaches decouple deblurring from 3D reconstruction, enabling the use of stand-alone deblurring algorithms such as Richardson-Lucy, DeepRFT, and Restormer. In this study, we evaluate the trade-offs between these strategies in terms of reconstruction quality, computational complexity, and suitability for varying levels of blur. Our findings reveal that modular approaches are more effective for low to medium blur scenarios, while Deblur-NeRF, a joint optimization framework, excels at handling extreme blur when computational costs are not a constraint.

Paper Citation

in Harvard Style

Malhotra A., Seghouani N., Saiid A., Almatuwa A. and Ganepola K. (2025). Rethinking Deblurring Strategies for 3D Reconstruction: Joint Optimization vs. Modular Approaches. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 816-823. DOI: 10.5220/0013378800003912

in Bibtex Style

@conference{visapp25,
author={Akash Malhotra and Nacéra Seghouani and Ahmad Saiid and Alaa Almatuwa and Koumudi Ganepola},
title={Rethinking Deblurring Strategies for 3D Reconstruction: Joint Optimization vs. Modular Approaches},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={816-823},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013378800003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Rethinking Deblurring Strategies for 3D Reconstruction: Joint Optimization vs. Modular Approaches
SN - 978-989-758-728-3
AU - Malhotra A.
AU - Seghouani N.
AU - Saiid A.
AU - Almatuwa A.
AU - Ganepola K.
PY - 2025
SP - 816
EP - 823
DO - 10.5220/0013378800003912
PB - SciTePress