liu.seSearch for publications in DiVA
Planned maintenance
A system upgrade is planned for 17/11-2026, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
High Frame Rate Video Synthesis using Event Cameras
Linköping University, Department of Electrical Engineering.
2026 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Höghastighetsvideo med stöd av eventkameror (Swedish)
Abstract [en]

High temporal resolution video is important in a variety of applications that involve objects in fast motion. These applications range from anything like the analysis of sports or animal behavior to the analysis of lightning and explosions. However, regular cameras are limited by frame rate and dynamic range due to bandwidth limitations, processing power, and data storage. Event cameras, on the other hand, address these limitations by providing microsecond temporal resolution at high dynamic range; however, event cameras are asynchronous and lack the texture rich appearance of standard images. What this study sets its focus on is event-based frame-interpolation. This study discusses the use of certain evaluation metrics for event-based frame interpolation and proposes two model architectures for the task, one relying on a continuous motion estimation through splines. The metrics, PSNR and SSIM, are used to evaluate the models on synthetic and real-world data as well as to investigate synthetic-to-real data transfer-learning. In addition, this thesis analyzes the effects of RGB-Event alignment errors from homography and model uncertainty based on the amount of movement. The findings suggest that synthetic-to-real data transfer learning is a good method for teaching a model the base-task of interpolation while alignment errors can make models unpredictable. Also reported is the relation between the amount of movement and the uncertainty of the models.

Place, publisher, year, edition, pages
2026. , p. 36
Keywords [en]
computer vision, frame interpolation, machine learning, event cameras, high speed video synthesis, artificial intelligence, event-based vision, high-speed imaging, motion estimation, image processing, spline-based motion estimation
National Category
Computer Vision and Learning Systems
Identifiers
URN: urn:nbn:se:liu:diva-224870ISRN: LiTH-ISY-EX--26/5851--SEOAI: oai:DiVA.org:liu-224870DiVA, id: diva2:2071735
Subject / course
Computer science
Presentation
2026-06-05, ISY Visionen, stora konferensrummet, Linköping Universitet, Campus Valla, Linköping, 13:15 (English)
Supervisors
Examiners
Available from: 2026-06-15 Created: 2026-06-14 Last updated: 2026-06-15Bibliographically approved

Open Access in DiVA

fulltext(17874 kB)303 downloads
File information
File name FULLTEXT01.pdfFile size 17874 kBChecksum SHA-512
d0d00a31daba631eeeaf09ec5f640de8d098380da39f441d161d053843f864c2d407e3c8115910d313c7aed638cda9e05a21127e0f07d5573a5366dad03bb905
Type fulltextMimetype application/pdf

By organisation
Department of Electrical Engineering
Computer Vision and Learning Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 303 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 149 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf