TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention

Tutkimustuotosvertaisarvioitu

Standard

OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention. / Liao, Kang; Lin, Chunyun; Zhao, Yao; Gabbouj, Moncef; Zheng, Yang.

julkaisussa: IEEE Journal of Selected Topics in Signal Processing, 22.11.2019.

Tutkimustuotosvertaisarvioitu

Harvard

Liao, K, Lin, C, Zhao, Y, Gabbouj, M & Zheng, Y 2019, 'OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention', IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/JSTSP.2019.2955017

APA

Liao, K., Lin, C., Zhao, Y., Gabbouj, M., & Zheng, Y. (2019). OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/JSTSP.2019.2955017

Vancouver

Liao K, Lin C, Zhao Y, Gabbouj M, Zheng Y. OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention. IEEE Journal of Selected Topics in Signal Processing. 2019 marras 22. https://doi.org/10.1109/JSTSP.2019.2955017

Author

Liao, Kang ; Lin, Chunyun ; Zhao, Yao ; Gabbouj, Moncef ; Zheng, Yang. / OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention. Julkaisussa: IEEE Journal of Selected Topics in Signal Processing. 2019.

Bibtex - Lataa

@article{d614752b960a4651b2165356491101f1,
title = "OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention",
abstract = "Omnidirectional cameras have recently received significant attention in panoramic imaging systems such as virtual reality (VR) technology; however, the strong geometric distortion in omnidirectional images severely affects the object recognition and semantic understanding. In this paper, we propose an automatic omnidirectional image distortion correction approach powered by a unified learning model (OIDC-Net). This approach is applicable for almost all types of omnidirectional cameras, requiring nothing more than a distorted image. A crucial and challenging ingredient for reconstructing the real physical scene is to estimate the heterogeneous distortion coefficients in an appropriate camera model. To address this issue, we present a novel coarse-to-fine region attention mechanism to alleviate the difficulty of predicting all coefficients simultaneously. With the proposed cascade structure and deep fusion strategy, the ambiguous relationship among these heterogeneous distortion coefficients has been incrementally perceived. Our experimental results show significant improvement over the state-of-the-art methods in terms of visual appearance, while maintaining a promising quantitative performance.",
keywords = "Omnidirectional image distortion correction, Coarse-to-fine region attention, Incremental perception",
author = "Kang Liao and Chunyun Lin and Yao Zhao and Moncef Gabbouj and Yang Zheng",
year = "2019",
month = "11",
day = "22",
doi = "10.1109/JSTSP.2019.2955017",
language = "English",
journal = "IEEE Journal of Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - OIDC-Net: Omnidirectional Image Distortion Correction via Coarse-to-fine Region Attention

AU - Liao, Kang

AU - Lin, Chunyun

AU - Zhao, Yao

AU - Gabbouj, Moncef

AU - Zheng, Yang

PY - 2019/11/22

Y1 - 2019/11/22

N2 - Omnidirectional cameras have recently received significant attention in panoramic imaging systems such as virtual reality (VR) technology; however, the strong geometric distortion in omnidirectional images severely affects the object recognition and semantic understanding. In this paper, we propose an automatic omnidirectional image distortion correction approach powered by a unified learning model (OIDC-Net). This approach is applicable for almost all types of omnidirectional cameras, requiring nothing more than a distorted image. A crucial and challenging ingredient for reconstructing the real physical scene is to estimate the heterogeneous distortion coefficients in an appropriate camera model. To address this issue, we present a novel coarse-to-fine region attention mechanism to alleviate the difficulty of predicting all coefficients simultaneously. With the proposed cascade structure and deep fusion strategy, the ambiguous relationship among these heterogeneous distortion coefficients has been incrementally perceived. Our experimental results show significant improvement over the state-of-the-art methods in terms of visual appearance, while maintaining a promising quantitative performance.

AB - Omnidirectional cameras have recently received significant attention in panoramic imaging systems such as virtual reality (VR) technology; however, the strong geometric distortion in omnidirectional images severely affects the object recognition and semantic understanding. In this paper, we propose an automatic omnidirectional image distortion correction approach powered by a unified learning model (OIDC-Net). This approach is applicable for almost all types of omnidirectional cameras, requiring nothing more than a distorted image. A crucial and challenging ingredient for reconstructing the real physical scene is to estimate the heterogeneous distortion coefficients in an appropriate camera model. To address this issue, we present a novel coarse-to-fine region attention mechanism to alleviate the difficulty of predicting all coefficients simultaneously. With the proposed cascade structure and deep fusion strategy, the ambiguous relationship among these heterogeneous distortion coefficients has been incrementally perceived. Our experimental results show significant improvement over the state-of-the-art methods in terms of visual appearance, while maintaining a promising quantitative performance.

KW - Omnidirectional image distortion correction

KW - Coarse-to-fine region attention

KW - Incremental perception

U2 - 10.1109/JSTSP.2019.2955017

DO - 10.1109/JSTSP.2019.2955017

M3 - Article

JO - IEEE Journal of Selected Topics in Signal Processing

JF - IEEE Journal of Selected Topics in Signal Processing

SN - 1932-4553

ER -