kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Diffusion Models for Video Prediction and Infilling: Training a conditional video diffusion model for arbitrary video completion tasks
KTH, School of Electrical Engineering and Computer Science (EECS).
2022 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Diffusionsmodeller för videoförutsägelse och ifyllnad : Träning av en villkorlig videodiffusionsmodell för slumpmässiga videokompletteringsuppgifter (Swedish)
Abstract [en]

To predict and anticipate future outcomes or reason about missing information in a sequence is a key ability for agents to be able to make intelligent decisions. This requires strong temporally coherent generative capabilities. Diffusion models have shown huge success in several generative tasks lately, but have not been extensively explored in the video domain. We present Random-Mask Video Diffusion (RaMViD), which extends image diffusion models to videos using 3D convolutions, and introduces a new conditioning technique during training. By varying the mask we condition on, the model is able to perform video prediction, infilling and upsampling. Since we do not use concatenation to condition on a mask, as done in most conditionally trained diffusion models, we are able to utilize the same architecture as used for unconditional training which allows us to train the model in a conditional and unconditional fashion at the same time. We evaluated the model on two benchmark datasets for video prediction, on which we achieve state-of-the-art results, and one for video generation.

Abstract [sv]

Att förutse framtida resultat eller resonera kring bristande information i en sekvens är en viktig förutsättning för agenter att göra intelligenta beslut. Detta kräver robusta temporärt koherenta generativa kapaciteter. Diffusionsmodeller har visat pa stor framgang i flera generativa uppgifter i närtid, men denna potential har inte utforskats grundligt i samband med video. Vi presenterar Random-Mask Video Diffusion (RaMViD), vilket bredar bilddiffusionsmodeller till video med hjälp av 3D konvolutioner, och introducerar en ny konditioneringsteknik under träning. Genom att variera masken vi tränar med kan modellen utföra videoförutsägelse och videoifyllnad. Eftersom vi inte använder konkatenering för att träna pa en mask, som görs i de flesta villkorstränade diffusionsmodeller, har vi möjlighet att använda samma arkiktektur som används för ovillkorad träning, vilket i sin tur tillater oss att träna modellen pa ett villkorat och ovillkorat sätt samtidigt. Vi utvärderade modellen pa tva benchmnark datasets för videoförutsägelse och en för videogenerering, varav pa den första vi uppnade de bästa kvantitativa resultaten bland samtida metoder.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology , 2022. , p. 46
Series
TRITA-EECS-EX ; 2022:864
Keywords [en]
Diffusion, Video prediction and infilling, Conditional generation
Keywords [sv]
Diffusion, Videoförutsägelse och ifyllnad, Villkorad generation
National Category
Computer Sciences Computer Engineering Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-323070OAI: oai:DiVA.org:kth-323070DiVA, id: diva2:1726971
Supervisors
Examiners
Available from: 2023-01-27 Created: 2023-01-14 Last updated: 2023-01-27Bibliographically approved

Open Access in DiVA

fulltext(4044 kB)743 downloads
File information
File name FULLTEXT01.pdfFile size 4044 kBChecksum SHA-512
ac3c9a657b657c7214246d2ddeecf92f51cb1c3b30035b9faeea887ff379b29779f79df1f227026bc7b04cfd766aec11c85c49002b4c974da0fe2032bf372530
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer SciencesComputer EngineeringComputer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 743 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: 596 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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