%AAittala, M%ASharma, P%AYedidia, A.%AMurmann, L.%AFreeman, W.%AWornell, G.%ADurand, F.%Anull Ed.%D2019%I %K %MOSTI ID: 10201538 %PMedium: X %TComputational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization %XWe 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.