Deterministic neural illumination mapping for efficient auto-white balance correction

Name: Deterministic neural illumination mapping for efficient auto-white balance correction
Author: Kınlı, Osman Furkan, Yılmaz, Doğa, Özcan, Barış, Kıraç, Mustafa Furkan

İsim	Deterministic neural illumination mapping for efficient auto-white balance correction
Yazar	Kınlı, Osman Furkan, Yılmaz, Doğa, Özcan, Barış, Kıraç, Mustafa Furkan
Basım Tarihi:	2023
Basım Yeri	- IEEE
Konu	Auto white balance correction, Deterministic color mapping, Reverse style transfer, Style factor
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835030744-3
Kayıt Numarası	d197508d-61d8-45db-99c4-72689d9b3bcd
Lokasyon	Computer Science
Tarih	2023
Örnek Metin	Auto-white balance (AWB) correction is a critical operation in image signal processors for accurate and consistent color correction across various illumination scenarios. This paper presents a novel and efficient AWB correction method that achieves at least 35 times faster processing with equivalent or superior performance on high-resolution images for the current state-of-the-art methods. Inspired by deterministic color style transfer, our approach introduces deterministic illumination color mapping, leveraging learnable projection matrices for both canonical illumination form and AWB-corrected output. It involves feeding high-resolution images and corresponding latent representations into a mapping module to derive a canonical form, followed by another mapping module that maps the pixel values to those for the corrected version. This strategy is designed as resolution-agnostic and also enables seamless integration of any pre-trained AWB network as the backbone. Experimental results confirm the effectiveness of our approach, revealing significant performance improvements and reduced time complexity compared to state-of-the-art methods. Our method provides an efficient deep learning-based AWB correction solution, promising real-time, high-quality color correction for digital imaging applications.
DOI	10.1109/ICCVW60793.2023.00122

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Deterministic neural illumination mapping for efficient auto-white balance correction

Yazar Kınlı, Osman Furkan, Yılmaz, Doğa, Özcan, Barış, Kıraç, Mustafa Furkan

Basım Tarihi 2023

Basım Yeri - IEEE

Konu Auto white balance correction, Deterministic color mapping, Reverse style transfer, Style factor

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835030744-3

Kayıt Numarası d197508d-61d8-45db-99c4-72689d9b3bcd

Lokasyon Computer Science

Tarih 2023

Örnek Metin Auto-white balance (AWB) correction is a critical operation in image signal processors for accurate and consistent color correction across various illumination scenarios. This paper presents a novel and efficient AWB correction method that achieves at least 35 times faster processing with equivalent or superior performance on high-resolution images for the current state-of-the-art methods. Inspired by deterministic color style transfer, our approach introduces deterministic illumination color mapping, leveraging learnable projection matrices for both canonical illumination form and AWB-corrected output. It involves feeding high-resolution images and corresponding latent representations into a mapping module to derive a canonical form, followed by another mapping module that maps the pixel values to those for the corrected version. This strategy is designed as resolution-agnostic and also enables seamless integration of any pre-trained AWB network as the backbone. Experimental results confirm the effectiveness of our approach, revealing significant performance improvements and reduced time complexity compared to state-of-the-art methods. Our method provides an efficient deep learning-based AWB correction solution, promising real-time, high-quality color correction for digital imaging applications.

DOI 10.1109/ICCVW60793.2023.00122