English

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

Computer Vision and Pattern Recognition 2019-12-06 v1 Machine Learning

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.

Keywords

Cite

@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

R2 v1 2026-06-23T12:36:19.909Z