loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Jose Campana ; Luís Decker ; Marcos Souza ; Helena Maia and Helio Pedrini

Affiliation: Institute of Computing, University of Campinas, Campinas, SP, 13083-852, Brazil

Keyword(s): Image Inpainting, Sketch-Pencil, Image Processing, Transformers.

Abstract: Image inpainting aims to realistically fill missing regions in images, which requires both structural and textural understanding. Traditionally, methods in the literature have employed Convolutional Neural Networks (CNN), especially Generative Adversarial Networks (GAN), to restore missing regions in a coherent and reliable manner. However, CNNs’ limited receptive fields can sometimes result in unreliable outcomes due to their inability to capture the broader context of the image. Transformer-based models, on the other hand, can learn long-range dependencies through self-attention mechanisms. In order to generate more consistent results, some approaches have further incorporated auxiliary information to guide the model’s understanding of structural information. In this work, we propose a new method for image inpainting that uses sketch-pencil information to guide the restoration of structural, as well as textural elements. Unlike previous works that employ edges, lines, or segmentati on maps, we leverage the sketch-pencil domain and the capabilities of Transformers to learn long-range dependencies to properly match structural and textural information, resulting in more consistent results. Experimental results show the effectiveness of our approach, demonstrating either superior or competitive performance when compared to existing methods, especially in scenarios involving complex images and large missing areas. (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 3.149.253.73

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:
Campana, J.; Decker, L.; Souza, M.; Maia, H. and Pedrini, H. (2024). Image Inpainting on the Sketch-Pencil Domain with Vision Transformers. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 122-132. DOI: 10.5220/0012363500003660

@conference{visapp24,
author={Jose Campana. and Luís Decker. and Marcos Souza. and Helena Maia. and Helio Pedrini.},
title={Image Inpainting on the Sketch-Pencil Domain with Vision Transformers},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={122-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012363500003660},
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 3: VISAPP
TI - Image Inpainting on the Sketch-Pencil Domain with Vision Transformers
SN - 978-989-758-679-8
IS - 2184-4321
AU - Campana, J.
AU - Decker, L.
AU - Souza, M.
AU - Maia, H.
AU - Pedrini, H.
PY - 2024
SP - 122
EP - 132
DO - 10.5220/0012363500003660
PB - SciTePress