SCENE GRAPH TO IMAGE GENERATION WITH CONTEXTUALIZED OBJECT LAYOUT REFINEMENT

Maor Ivgi, Yaniv Benny, Avichai Ben-David, Jonathan Berant, Lior Wolf

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

Generating images from scene graphs is a challenging task that attracted substantial interest recently. Prior works have approached this task by generating an intermediate layout description of the target image. However, the representation of each object in the layout was generated independently, which resulted in high overlap, low coverage, and an overall blurry layout. We propose a novel method that alleviates these issues by generating the entire layout description gradually to improve inter-object dependency. We empirically show on the COCO-STUFF dataset that our approach improves the quality of both the intermediate layout and the final image. Our approach improves the layout coverage by almost 20 points, and drops object overlap to negligible amounts. Our code is available at github.com/yanivbenny/COLoR.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Pages2428-2432
Number of pages5
ISBN (Electronic)9781665441155
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: 19 Sep 202122 Sep 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21

Funding

FundersFunder number
Yandex Initiative for Machine Learning
Horizon 2020 Framework Programme
European Commission
Horizon 2020802800, 725974

    Keywords

    • GAN
    • Image synthesis
    • Scene graph

    Fingerprint

    Dive into the research topics of 'SCENE GRAPH TO IMAGE GENERATION WITH CONTEXTUALIZED OBJECT LAYOUT REFINEMENT'. Together they form a unique fingerprint.

    Cite this