Local Texture Estimator for Implicit Representation Function

Jaewon Lee; Kyong Hwan Jin

doi:10.1109/CVPR52688.2022.00197

Local Texture Estimator for Implicit Representation Function

Jaewon Lee
, Kyong Hwan Jin

Department of Electrical Engineering and Computer Science

Daegu Gyeongbuk Institute of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

180 Scopus citations

Abstract

Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propose a Local Texture Estimator (LTE), a dominant-frequency estimator for natural images, enabling an implicit function to capture fine details while reconstructing images in a continuous manner. When jointly trained with a deep super-resolution (SR) architecture, LTE is capable of characterizing image textures in 2D Fourier space. We show that an LTE-based neuralfunction achieves favorable performance against existing deep SR methods within an arbitrary-scale factor. Furthermore, we demonstrate that our implementation takes the shortest running time compared to previous works.

Original language	English
Title of host publication	Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Publisher	IEEE Computer Society
Pages	1919-1928
Number of pages	10
ISBN (Electronic)	9781665469463
DOIs	https://doi.org/10.1109/CVPR52688.2022.00197
State	Published - 2022
Event	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States Duration: 19 Jun 2022 → 24 Jun 2022

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2022-June
ISSN (Print)	1063-6919

Conference

Conference	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Country/Territory	United States
City	New Orleans
Period	19/06/22 → 24/06/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Deep learning architectures and techniques
Explainable computer vision
Low-level vision

Access to Document

10.1109/CVPR52688.2022.00197

Cite this

Lee, J., & Jin, K. H. (2022). Local Texture Estimator for Implicit Representation Function. In Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 (pp. 1919-1928). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2022-June). IEEE Computer Society. https://doi.org/10.1109/CVPR52688.2022.00197

@inproceedings{006d2285e5e248878ee2daa915e8edbb,

title = "Local Texture Estimator for Implicit Representation Function",

abstract = "Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propose a Local Texture Estimator (LTE), a dominant-frequency estimator for natural images, enabling an implicit function to capture fine details while reconstructing images in a continuous manner. When jointly trained with a deep super-resolution (SR) architecture, LTE is capable of characterizing image textures in 2D Fourier space. We show that an LTE-based neuralfunction achieves favorable performance against existing deep SR methods within an arbitrary-scale factor. Furthermore, we demonstrate that our implementation takes the shortest running time compared to previous works.",

keywords = "Deep learning architectures and techniques, Explainable computer vision, Low-level vision",

author = "Jaewon Lee and Jin, \{Kyong Hwan\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 ; Conference date: 19-06-2022 Through 24-06-2022",

year = "2022",

doi = "10.1109/CVPR52688.2022.00197",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "1919--1928",

booktitle = "Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022",

}

Lee, J & Jin, KH 2022, Local Texture Estimator for Implicit Representation Function. in Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2022-June, IEEE Computer Society, pp. 1919-1928, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, United States, 19/06/22. https://doi.org/10.1109/CVPR52688.2022.00197

Local Texture Estimator for Implicit Representation Function. / Lee, Jaewon; Jin, Kyong Hwan.
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. IEEE Computer Society, 2022. p. 1919-1928 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2022-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Local Texture Estimator for Implicit Representation Function

AU - Lee, Jaewon

AU - Jin, Kyong Hwan

PY - 2022

Y1 - 2022

N2 - Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propose a Local Texture Estimator (LTE), a dominant-frequency estimator for natural images, enabling an implicit function to capture fine details while reconstructing images in a continuous manner. When jointly trained with a deep super-resolution (SR) architecture, LTE is capable of characterizing image textures in 2D Fourier space. We show that an LTE-based neuralfunction achieves favorable performance against existing deep SR methods within an arbitrary-scale factor. Furthermore, we demonstrate that our implementation takes the shortest running time compared to previous works.

AB - Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propose a Local Texture Estimator (LTE), a dominant-frequency estimator for natural images, enabling an implicit function to capture fine details while reconstructing images in a continuous manner. When jointly trained with a deep super-resolution (SR) architecture, LTE is capable of characterizing image textures in 2D Fourier space. We show that an LTE-based neuralfunction achieves favorable performance against existing deep SR methods within an arbitrary-scale factor. Furthermore, we demonstrate that our implementation takes the shortest running time compared to previous works.

KW - Deep learning architectures and techniques

KW - Explainable computer vision

KW - Low-level vision

UR - https://www.scopus.com/pages/publications/85141304166

U2 - 10.1109/CVPR52688.2022.00197

DO - 10.1109/CVPR52688.2022.00197

M3 - Conference contribution

AN - SCOPUS:85141304166

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1919

EP - 1928

BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

PB - IEEE Computer Society

T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

Y2 - 19 June 2022 through 24 June 2022

ER -

Local Texture Estimator for Implicit Representation Function

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this