Skip to yearly menu bar Skip to main content


Poster

Non-parametric Sensor Noise Modeling and Synthesis

Ali Mosleh · Luxi Zhao · Atin Vikram Singh · Jaeduk Han · Abhijith Punnappurath · Marcus A Brubaker · Jihwan Choe · Michael S Brown

# 223
Strong blind review: This paper was not made available on public preprint services during the review process Strong Double Blind
[ ] [ Paper PDF ]
[ Supplemental] 
Tue 1 Oct 7:30 a.m. PDT — 9:30 a.m. PDT

Abstract:

We introduce a novel non-parametric sensor noise model that directly constructs probability mass functions per intensity level from captured images. We show that our noise model provides a more accurate fit to real sensor noise than existing models. We detail the capture procedure for deriving our non-parametric noise model and introduce an interpolation method that reduces the number of ISOs levels that need to be captured. In addition, we propose a method to synthesize noise on existing noisy images when noise-free images are not available. Our noise model is straightforward to calibrate and provides notable improvements over competing noise models on downstream tasks.

Chat is not available.