Deep Joint Deinterlacing and Denoising for Single Shot Dual-ISO HDR Reconstruction

Date

2020-01-01

Author

Cogalan, Ugur
Akyüz, Ahmet Oğuz

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

222
views

0
downloads

HDR images have traditionally been obtained by merging multiple exposures each captured with a different exposure time. However, this approach entails longer capture times and necessitates deghosting if the captured scene contains moving objects. With the advent of modern camera sensors that can perform per-pixel exposure modulation, it is now possible to capture all of the required exposures within a single shot. The new challenge then becomes how to best combine different pixels with different exposure values into a single full-resolution and low-noise HDR image. We propose a joint multi-exposure frame deinterlacing and denoising algorithm powered by deep convolutional neural networks (DCNN). In our algorithm, we first train two DCNNs, with one tuned for reconstructing low exposures and the other for high exposures. Each DCNN takes the same mosaicked dual-ISO input image and outputs either the low exposure or high exposure depending on the type of the network. The resulting exposures can be demosaicked and converted to the desired target color space prior to HDR assembly. Our evaluations indicate that the quality of our results significantly surpasses the state-of-the-art in single-image HDR reconstruction algorithms.

Subject Keywords

Software, Computer Graphics and Computer-Aided Design

URI

https://hdl.handle.net/11511/48281

Journal

IEEE TRANSACTIONS ON IMAGE PROCESSING

DOI

https://doi.org/10.1109/tip.2020.3004014

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Deep joint deinterlacing and denoising for single shot dual-ISO HDR reconstruction Çoğalan, Uğur; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2019) HDR (High Dynamic Range) images have traditionally been obtained by merging multiple exposures each captured with a different exposure time. However, this approach entails longer capture times and necessitates deghosting if the captured scene contains moving objects. With the advent of modern camera sensors that can perform per-pixel exposure modulation, it is now possible to capture all of the required exposures within a single shot. The new challenge then becomes how to best combine different pixels with ...
Noise reduction in high dynamic range imaging Akyüz, Ahmet Oğuz (Elsevier BV, 2007-10-01) A common method to create high dynamic range (HDR) images is to combine several different exposures of the same scene. In this approach, the use of higher ISO settings will reduce exposure times, and thereby the total capture time. This is advantageous in certain environments where it may help minimize ghosting artifacts. However, exposures taken at high sensitivity settings tend to be noisy, which is further amplified by the HDR creation algorithm. We present a robust and efficient technique to significant...
Watermarking of Free-view Video Koz, Alper; Cigla, Cevahir; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2010-07-01) With the advances in image based rendering (IBR) in recent years, generation of a realistic arbitrary view of a scene from a number of original views has become cheaper and faster. One of the main applications of this progress has emerged as free-view TV(FTV), where TV-viewers select freely the viewing position and angle via IBR on the transmitted multiview video. Noting that the TV-viewer might record a personal video for this arbitrarily selected view and misuse this content, it is apparent that copyright...
Good Features to Correlate for Visual Tracking Gundogdu, Erhan; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2018-05-01) During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in this family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize the robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learni...
Accelerating Translational Image Registration for HDR Images on GPU Alpay, Kadir Cenk; Temizel, Alptekin (null; 2020-10-09) High Dynamic Range (HDR) images are generated using multiple exposures of a scene. When a hand-held camera is used to capture a static scene, these images need to be aligned by globally shifting each image in both dimensions. For a fast and robust alignment, the shift amount is commonly calculated using Median Threshold Bitmaps (MTB) and creating an image pyramid. In this study, we optimize these computations using a parallel processing approach utilizing GPU. Experimental evaluation shows that the proposed...

Citation Formats

U. Cogalan and A. O. Akyüz, “Deep Joint Deinterlacing and Denoising for Single Shot Dual-ISO HDR Reconstruction,” IEEE TRANSACTIONS ON IMAGE PROCESSING, pp. 7511–7524, 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48281.