Four-dimensional video imaging via generative deep learning and a diffuser-encoded image sensor
Abstract
Light carries rich information across space, spectrum, polarization, and time, yet conventional cameras capture only a narrow projection of this multidimensional structure. A thin diffuser encodes wavelength-dependent information into single-shot scatterograms, captured by a polarization-resolving CMOS sensor that simultaneously measures four linear polarization states. We use 4DCam to image a live Betta splendens fish, uncovering polarization-dependent color modulations that remain invisible to conventional cameras. We experimentally show that the 4D information encoded in the scatterograms markedly improves material discrimination, achieving 96% accuracy for textile classification and 90% for camouflage detection, compared with 70% and 80%, respectively, using 3D hyperspectral imaging alone. Built entirely from passive optics, 4DCam seamlessly integrates physical encoding, generative decoding, and direct inference, enabling real-time, information-complete optical sensing.
Cite
@article{arxiv.2601.12162,
title = {Four-dimensional video imaging via generative deep learning and a diffuser-encoded image sensor},
author = {Max T. Kauss and William Walker and Alexander Ingold and Jakob Dammann and Apratim Majumder and Rajesh Menon},
journal= {arXiv preprint arXiv:2601.12162},
year = {2026}
}