English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models

MPS-Authors
/persons/resource/persons250029

Çoğalan,  Uğur
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons232942

Bemana,  Mojtaba
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45095

Myszkowski,  Karol
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

arXiv:2012.12009.pdf
(Preprint), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Çoğalan, U., Bemana, M., Myszkowski, K., Seidel, H.-P., & Ritschel, T. (2020). HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models. Retrieved from https://arxiv.org/abs/2012.12009.


Cite as: http://hdl.handle.net/21.11116/0000-0007-B721-5
Abstract
We seek to reconstruct sharp and noise-free high-dynamic range (HDR) video from a dual-exposure sensor that records different low-dynamic range (LDR) information in different pixel columns: Odd columns provide low-exposure, sharp, but noisy information; even columns complement this with less noisy, high-exposure, but motion-blurred data. Previous LDR work learns to deblur and denoise (DISTORTED->CLEAN) supervised by pairs of CLEAN and DISTORTED images. Regrettably, capturing DISTORTED sensor readings is time-consuming; as well, there is a lack of CLEAN HDR videos. We suggest a method to overcome those two limitations. First, we learn a different function instead: CLEAN->DISTORTED, which generates samples containing correlated pixel noise, and row and column noise, as well as motion blur from a low number of CLEAN sensor readings. Second, as there is not enough CLEAN HDR video available, we devise a method to learn from LDR video in-stead. Our approach compares favorably to several strong baselines, and can boost existing methods when they are re-trained on our data. Combined with spatial and temporal super-resolution, it enables applications such as re-lighting with low noise or blur.