Publication:
Burst photography for learning to enhance extremely dark images

Thumbnail Image

Departments

School / College / Institute

Program

KU-Authors

KU Authors

Co-Authors

Karadeniz, Ahmet Serdar
Erdem, Erkut

Publication Date

Language

Embargo Status

NO

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently, learning-based approaches have shown very promising results for this task since they have substantially more expressive capabilities to allow for improved quality. Motivated by these studies, in this paper, we aim to leverage burst photography to boost the performance and obtain much sharper and more accurate RGB images from extremely dark raw images. The backbone of our proposed framework is a novel coarse-to-fine network architecture that generates high-quality outputs progressively. The coarse network predicts a low-resolution, denoised raw image, which is then fed to the fine network to recover fine-scale details and realistic textures. To further reduce the noise level and improve the color accuracy, we extend this network to a permutation invariant structure so that it takes a burst of low-light images as input and merges information from multiple images at the feature-level. Our experiments demonstrate that our approach leads to perceptually more pleasing results than the state-of-the-art methods by producing more detailed and considerably higher quality images.

Source

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer science, Artificial intelligence, Engineering, Electrical and electronic

Citation

Has Part

Source

IEEE Transactions on Image Processing

Book Series Title

Edition

DOI

10.1109/TIP.2021.3125394

item.page.datauri

Link

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

0

Views

6

Downloads

View PlumX Details