We are experiencing some difficulties with our submission forms, which we are working to resolve. If you have any issues, please contact us at dspace-lib@mit.edu.

Computational mirrors: Blind inverse light transport by deep matrix factorization

Thumbnail Image
Download
Name

NeurIPS-2019-computational-mirrors-blind-inverse-light-transport-by-deep-matrix-factorization-Paper.pdf

Description
Published version
Size

1.49 MB

Format

Adobe PDF

Checksum (MD5)

75486a275b5b7168f68bbf0eceb418b4

sword-2020-12-11T16:56:18.original.xml (130 B)
Original SWORD entry document
Author(s)
Aittala, Miika
•
Sharma, Prafull
•
Murmann, Lukas
•
Yedidia, Adam B.
•
Wornell, Gregory W.
•
Freeman, William T
•
Durand, Frederic
Journal
Advances in Neural Information Processing Systems
Publisher
Morgan Kaufmann Publishers
Citation
Aittala, Miika et al. “Computational mirrors: Blind inverse light transport by deep matrix factorization.” Advances in Neural Information Processing Systems, 32 (November 2019) © 2019 The Author(s)
Version
Final published version
Abstract
We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region. We solve this problem by factoring the observed video into a matrix product between the unknown hidden scene video and an unknown light transport matrix. This task is extremely ill-posed as any non-negative factorization will satisfy the data. Inspired by recent work on the Deep Image Prior, we parameterize the factor matrices using randomly initialized convolutional neural networks trained in a one-off manner, and show that this results in decompositions that reflect the true motion in the hidden scene.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2019/hash/5a2afca61e35f45a7dd44ca46e0225f4-Abstract.html
PrivacyPermissionsAccessibilityContact us
Notify us about copyright concerns.