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.
@article{arxiv.1912.02314,
title = {Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization},
author = {Miika Aittala and Prafull Sharma and Lukas Murmann and Adam B. Yedidia and Gregory W. Wornell and William T. Freeman and Fredo Durand},
journal= {arXiv preprint arXiv:1912.02314},
year = {2019}
}
Comments
14 pages, 5 figures, Advances in Neural Information Processing Systems 2019