loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Ryosuke Miyake ; Tetsu Matsukawa and Einoshin Suzuki

Affiliation: Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan

Keyword(s): Image Generation, Hyper Scene Graph, Object Attention.

Abstract: Conditional image generation, which aims to generate consistent images with a user’s input, is one of the critical problems in computer vision. Text-to-image models have succeeded in generating realistic images for simple situations in which a few objects are present. Yet, they often fail to generate consistent images for texts representing complex situations. Scene-graph-to-image models have the advantage of generating images for complex situations based on the structure of a scene graph. We extended a scene-graph-to-image model to an image generation model from a hyper scene graph with trinomial hyperedges. Our model, termed hsg2im, improved the consistency of the generated images. However, hsg2im has difficulty in generating natural and consistent images for hyper scene graphs with many objects. The reason is that the graph convolutional network in hsg2im struggles to capture relations of distant objects. In this paper, we propose a novel image generation model which addresses thi s shortcoming by introducing object attention layers. We also use a layout-to-image model auxiliary to generate higher-resolution images. Experimental validations on COCO-Stuff and Visual Genome datasets show that the proposed model generates more natural and consistent images to user’s inputs than the cutting-edge hyper scene-graph-to-image model. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.144.181.249

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Miyake, R.; Matsukawa, T. and Suzuki, E. (2024). Image Generation from Hyper Scene Graphs with Trinomial Hyperedges Using Object Attention. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 266-279. DOI: 10.5220/0012472500003660

@conference{visapp24,
author={Ryosuke Miyake. and Tetsu Matsukawa. and Einoshin Suzuki.},
title={Image Generation from Hyper Scene Graphs with Trinomial Hyperedges Using Object Attention},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={266-279},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012472500003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Image Generation from Hyper Scene Graphs with Trinomial Hyperedges Using Object Attention
SN - 978-989-758-679-8
IS - 2184-4321
AU - Miyake, R.
AU - Matsukawa, T.
AU - Suzuki, E.
PY - 2024
SP - 266
EP - 279
DO - 10.5220/0012472500003660
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic