UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging
Chu Zhou, Hang Zhao, Jin Han, Chang Xu, Chao Xu, Tiejun Huang, Boxin Shi
Abstract
A conventional camera often suffers from over- or under-exposure when recording a real-world scene with a very high dynamic range (HDR). In contrast, a modulo camera with a Markov random field (MRF) based unwrapping algorithm can theoretically accomplish unbounded dynamic range but shows degenerate performances when there are modulus-intensity ambiguity, strong local contrast, and color misalignment. In this paper, we reformulate the modulo image unwrapping problem into a series of binary labeling problems and propose a modulo edge-aware model, named as UnModNet, to iteratively estimate the binary rollover masks of the modulo image for unwrapping. Experimental results show that our approach can generate 12-bit HDR images from 8-bit modulo images reliably, and runs much faster than the previous MRF-based algorithm thanks to the GPU acceleration.
BibTeX
@inproceedings{NEURIPS2020_1102a326,
author = {Zhou, Chu and Zhao, Hang and Han, Jin and Xu, Chang and Xu, Chao and Huang, Tiejun and Shi, Boxin},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {1559--1570},
publisher = {Curran Associates, Inc.},
title = {UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/1102a326d5f7c9e04fc3c89d0ede88c9-Paper.pdf},
volume = {33},
year = {2020}
}