Burst Imaging with Learned Continuous Kernels
Name
biscarrat-cjbisc-sm-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
19.47 MB
Format
Adobe PDF
Checksum (MD5)
4b9c61925c2ef995df8722185063e259
Author(s)
Biscarrat, Camille
Advisor(s)
Durand, Frédo
Date Issued
September 2024
Publisher
Massachusetts Institute of Technology
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
