Timezone: »

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

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1150

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.

Author Information

Chu Zhou (Peking University)
Hang Zhao (MIT)
Jin Han (Peking University)
Chang Xu (University of Sydney)
Chao Xu (Peking University)
Tiejun Huang (Peking University)
Boxin Shi (Peking University)

More from the Same Authors