Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
Name
Miika_Aittala_Burst_Image_Deblurring_ECCV_2018_paper.pdf
Description
Accepted version
Size
4.32 MB
Format
Unknown
Checksum (MD5)
94adaeddb9c56852990e527bd1a5fd5c
Author(s)
Aittala, Miika
Durand, Fredo
Date Issued
2018
Publisher
Springer International Publishing
Citation
Aittala, Miika and Durand, Frédo. 2018. "Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks."
Version
Author's final manuscript
Abstract
© Springer Nature Switzerland AG 2018. We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image. Our novel convolutional architecture has a simultaneous view of all frames in the burst, and by construction treats them in an order-independent manner. This enables it to effectively detect and leverage subtle cues scattered across different frames, while ensuring that each frame gets a full and equal consideration regardless of its position in the sequence. We train the network with richly varied synthetic data consisting of camera shake, realistic noise, and other common imaging defects. The method demonstrates consistent state of the art burst image restoration performance for highly degraded sequences of real-world images, and extracts accurate detail that is not discernible from any of the individual frames in isolation.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01237-3_45
