Leveraging Pixel Value Certainty in Pixel-Shift and Other Multi-Shot Super-Resolution Processing

Research output: Contribution to journalConference articlepeer-review

Abstract

Traditional super-resolution processing computes sub-pixel alignment over a sequence of image captures to allow sampling at a finer spatial resolution. Alternatively, the mechanism intended to implement in-body image stabilization (IBIS) can be used to shift the sensor in a stationary camera by precise fractions of a pixel between exposures. The implicitly perfect alignment of pixel-shift images reduces post-processing to interleaving of raw data, but motion of camera or scene elements produces disturbing artifacts. Determining misalignments on raw images from cameras using color filter array (CFA) sensors is potentially problematic, so the synthesized super-resolution image is instead typically built from already-interpolated image data, with a reduction in tonal quality. The current work instead directly models the certainty, or confidence, with which pixel values are known. Sub-pixel alignment may be computed on either raw or interpolated image data. Still, only the underlying raw samples have precisely known values, so only they are used to compute the super-resolution image. However, primarily due to motion, even raw pixel values can have variable value certainty. Thus, a confidence metric is calculated for each raw pixel value and used as a weighting factor in computing the best estimate for the value of each super-resolution pixel.

Original languageEnglish
Article number142
JournalIS and T International Symposium on Electronic Imaging Science and Technology
Volume36
Issue number15
DOIs
StatePublished - 2024
EventIS and T International Symposium on Electronic Imaging 2024: 22nd Computational Imaging, COIMG 2024 - San Francisco, United States
Duration: Jan 21 2024Jan 25 2024

Bibliographical note

Publisher Copyright:
© 2024 Society for Imaging Science and Technology. All rights reserved.

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Fingerprint

Dive into the research topics of 'Leveraging Pixel Value Certainty in Pixel-Shift and Other Multi-Shot Super-Resolution Processing'. Together they form a unique fingerprint.

Cite this