loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Keisuke Toida 1 ; Naoki Kato 2 ; Osamu Segawa 2 ; Takeshi Nakamura 2 and Kazuhiro Hotta 1

Affiliations: 1 Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan ; 2 Chubu Electric Power Co., Inc., 1-1 Higashishin-cho, Higashi-ku, Nagoya 461-8680, Japan

Keyword(s): Variational Autoencoder, Homography Transformation, Unsupervised Learning.

Abstract: We propose Homography VAE, a novel architecture that combines Variational AutoEncoders with Homog-raphy transformation for unsupervised standardized view image reconstruction. By incorporating coordinate transformation into the VAE framework, our model decomposes the latent space into feature and transformation components, enabling the generation of consistent standardized view from multi-viewpoint images without explicit supervision. Effectiveness of our approach is demonstrated through experiments on MNIST and GRID datasets, where standardized reconstructions show significantly improved consistency across all evaluation metrics. For the MNIST dataset, the cosine similarity among standardized view achieved 0.66, while original and transformed views show 0.29 and 0.37, respectively. The number of PCA components required to explain 95% of the variance decreases from 193.5 to 33.2, indicating more consistent representations. Even more pronounced improvements are observed on GRID datase t, in which standardized view achieved a cosine similarity of 0.92 and required only 7 PCA components compared to 167 for original images. Furthermore, the first principal component of standardized view explains 71% of the total variance, suggesting highly consistent geometric patterns. These results validate that Homography VAE successfully learns to generate consistent standardized view representations from various viewpoints without requiring ground truth Homog-raphy matrices. (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 3.128.199.58

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:
Toida, K., Kato, N., Segawa, O., Nakamura, T. and Hotta, K. (2025). Homography VAE: Automatic Bird’s Eye View Image Reconstruction from Multi-Perspective Views. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3; ISSN 2184-4321, SciTePress, pages 626-632. DOI: 10.5220/0013244800003912

@conference{visapp25,
author={Keisuke Toida and Naoki Kato and Osamu Segawa and Takeshi Nakamura and Kazuhiro Hotta},
title={Homography VAE: Automatic Bird’s Eye View Image Reconstruction from Multi-Perspective Views},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={626-632},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013244800003912},
isbn={978-989-758-728-3},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Homography VAE: Automatic Bird’s Eye View Image Reconstruction from Multi-Perspective Views
SN - 978-989-758-728-3
IS - 2184-4321
AU - Toida, K.
AU - Kato, N.
AU - Segawa, O.
AU - Nakamura, T.
AU - Hotta, K.
PY - 2025
SP - 626
EP - 632
DO - 10.5220/0013244800003912
PB - SciTePress