Adjust Your Focus: Defocus Deblurring from Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation

Swami, K (2024) Adjust Your Focus: Defocus Deblurring from Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation. In: 8th International Conference on Computer Vision and Image Processing, CVIP 2023, 3 November 2023through 5 November 2023, Jammu, Indian, pp. 318-330.

PDF Com_com_inf_sci_CVIP_2024.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Defocus blur is a common problem in photography. It arises when an image is captured with a wide aperture, resulting in a shallow depth of field. Sometimes it is desired, e.g., in portrait effect. Otherwise, it is a problem from both an aesthetic point of view and downstream computer vision tasks, such as segmentation and depth estimation. Defocusing an out-of-focus image to obtain an all-in-focus image is a highly challenging and often ill-posed problem. A recent work exploited dual-pixel (DP) image information, widely available in consumer DSLRs and high-end smartphones, to solve the problem of defocus deblurring. DP sensors result in two sub-aperture views containing defocus disparity cues. A given pixel�s disparity is directly proportional to the distance from the focal plane. However, the existing methods adopt a naïve approach of a channel-wise concatenation of the two DP views without explicitly utilizing the disparity cues within the network. In this work, we propose to perform an explicit cross-correlation between the two DP views to guide the network for appropriate deblurring in different image regions. We adopt multi-scale cross-correlation to handle blur and disparities at different scales. Quantitative and qualitative evaluation of our multi-scale cross-correlation network (MCCNet) reveals that it achieves better defocus deblurring than existing state-of-the-art methods despite having lesser computational complexity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Item Type:	Conference Paper
Publication:	Communications in Computer and Information Science
Publisher:	Springer Science and Business Media Deutschland GmbH
Additional Information:	The copyright for this article belongs to the publisher.
Keywords:	Image enhancement, All-in-focus image; Cross-correlations; Deblurring; Defocus; Defocus blur; Defocus deblurring; Dual-pixel sensor; Multi-scales; Pixel images; Pixel sensors, Pixels
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	30 Aug 2024 10:57
Last Modified:	30 Aug 2024 10:57
URI:	http://eprints.iisc.ac.in/id/eprint/86048

Actions (login required)

View Item