Back to results

Massachusetts Institute of Technology

Burst Imaging with Learned Continuous Kernels

Abstract

dc:description.abstract

Burst imaging is a technique that consists of taking multiple images in quick succession and merging them into one output image. By aligning and combining data from multiple frames, we can increase resolution, attenuate noise, reduce motion blur and expand the dynamic range to obtain a higher quality image. In this thesis, we propose a method that learns continuous kernels to process and merge burst frames. We show that the learned kernels adapt to local image information and take advantage of sub-pixel sample location information to demosaic, denoise and merge the burst into a high quality output.

Degree

thesis:*
Name thesis:degree_name
Master
Department dc:contributor.department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Grantor dc:publisher
Massachusetts Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Biscarrat, Camille
Advisor dc:contributor.advisor
  • Durand, Frédo

Rights

dc:rights
Statement dc:rights
  • In Copyright - Educational Use Permitted
  • Copyright retained by author(s)

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1721.1/158488
OAI identifier oai:identifier
oai:dspace.mit.edu:1721.1/158488

Chain of custody

source
Harvested from
MIT
Base URL
dspace.mit.edu/oai/request
Last updated
2026-07-22
Source record
OAI-PMH GetRecord
related terms
citation

Biscarrat, Camille. Burst Imaging with Learned Continuous Kernels. Massachusetts Institute of Technology, 2024. https://hdl.handle.net/1721.1/158488