MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding

Haley M. So, Julien N.P. Martel, Gordon Wetzstein, Piotr Dudek

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

The ability to image high-dynamic-range (HDR) scenes is crucial in many computer vision applications. The dynamic range of conventional sensors, however, is fundamentally limited by their well capacity, resulting in saturation of bright scene parts. To overcome this limitation, emerging sensors offer in-pixel processing capabilities to encode the incident irradiance. Among the most promising encoding schemes is modulo wrapping, which results in a computational photography problem where the HDR scene is computed by an irradiance unwrapping algorithm from the wrapped low-dynamic-range (LDR) sensor image. Here, we design a neural network-based algorithm that outperforms previous irradiance unwrapping methods and we design a perceptually inspired 'mantissa,' or log-modulo, encoding scheme that more efficiently wraps an HDR scene into an LDR sensor. Combined with our reconstruction framework, MantissaCam achieves state-of-the-art results among modulo-type snapshot HDR imaging approaches. We demonstrate the efficacy of our method in simulation and show benefits of our algorithm on modulo images captured with a prototype implemented with a programmable sensor.

Original languageEnglish
Title of host publicationIEEE International Conference on Computational Photography, ICCP 2022
PublisherIEEE
ISBN (Electronic)9781665458511
DOIs
Publication statusPublished - 1 Aug 2022
Event14th IEEE International Conference on Computational Photography, ICCP 2022 - Pasadena, United States
Duration: 1 Aug 20225 Aug 2022

Publication series

NameIEEE International Conference on Computational Photography, ICCP 2022

Conference

Conference14th IEEE International Conference on Computational Photography, ICCP 2022
Country/TerritoryUnited States
CityPasadena
Period1/08/225/08/22

Keywords

  • computational photography
  • end-to-end optimization
  • in-pixel intelligence
  • programmable sensors

Fingerprint

Dive into the research topics of 'MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding'. Together they form a unique fingerprint.

Cite this