Depth-Aware Image Compositing Model for Parallax Camera Motion Blur

German F. Torres; Joni Kämäräinen

doi:10.1007/978-3-031-31435-3_19

Depth-Aware Image Compositing Model for Parallax Camera Motion Blur

German F. Torres, Joni Kämäräinen

Computing Sciences

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

1 Citation (Scopus)

1 Downloads (Pure)

Abstract

Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent spatially varying blur. The (forward) model produces realistic motion blur from a single image, depth map, and camera trajectory. Furthermore, we utilize the ICB model, combined with a coordinate-based MLP, to learn a sharp neural representation from the blurred input. Experimental results are reported for synthetic and real examples. The results verify that the ICB forward model is computationally efficient and produces realistic blur, despite the lack of occlusion information. Additionally, our method for restoring a sharp representation proves to be a competitive approach for the deblurring task.

Original language	English
Title of host publication	Image Analysis
Subtitle of host publication	22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, Proceedings, Part I.
Editors	Rikke Gade, Michael Felsberg, Joni-Kristian Kämäräinen
Publisher	Springer
Pages	279-296
Number of pages	18
Edition	1
ISBN (Electronic)	9783031314353
ISBN (Print)	9783031314346
DOIs	https://doi.org/10.1007/978-3-031-31435-3_19
Publication status	Published - 2023
Publication type	A4 Article in conference proceedings
Event	Scandinavian Conference on Image Analysis - Lapland, Finland Duration: 18 Apr 2023 → 21 Apr 2023

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Cham
Volume	13885 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Scandinavian Conference on Image Analysis
Country/Territory	Finland
City	Lapland
Period	18/04/23 → 21/04/23

Keywords

blur formation
deblurring
image compositing blur
neural representations

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-031-31435-3_19

Depth-Aware Image Compositing Model
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 3.84 MBLicence: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202310259099Licence: Unspecified

Cite this

Torres, G. F., & Kämäräinen, J. (2023). Depth-Aware Image Compositing Model for Parallax Camera Motion Blur. In R. Gade, M. Felsberg, & J.-K. Kämäräinen (Eds.), Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, Proceedings, Part I. (1 ed., pp. 279-296). (Lecture Notes in Computer Science; Vol. 13885 LNCS). Springer. https://doi.org/10.1007/978-3-031-31435-3_19

Torres, German F. ; Kämäräinen, Joni. / Depth-Aware Image Compositing Model for Parallax Camera Motion Blur. Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, Proceedings, Part I.. editor / Rikke Gade ; Michael Felsberg ; Joni-Kristian Kämäräinen. 1. ed. Springer, 2023. pp. 279-296 (Lecture Notes in Computer Science).

@inproceedings{0320755f3e3247509366f0b448f5ff69,

title = "Depth-Aware Image Compositing Model for Parallax Camera Motion Blur",

abstract = "Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent spatially varying blur. The (forward) model produces realistic motion blur from a single image, depth map, and camera trajectory. Furthermore, we utilize the ICB model, combined with a coordinate-based MLP, to learn a sharp neural representation from the blurred input. Experimental results are reported for synthetic and real examples. The results verify that the ICB forward model is computationally efficient and produces realistic blur, despite the lack of occlusion information. Additionally, our method for restoring a sharp representation proves to be a competitive approach for the deblurring task.",

keywords = "blur formation, deblurring, image compositing blur, neural representations",

author = "Torres, {German F.} and Joni K{\"a}m{\"a}r{\"a}inen",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Scandinavian Conference on Image Analysis ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1007/978-3-031-31435-3_19",

language = "English",

isbn = "9783031314346",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "279--296",

editor = "Rikke Gade and Michael Felsberg and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",

booktitle = "Image Analysis",

edition = "1",

}

Torres, GF & Kämäräinen, J 2023, Depth-Aware Image Compositing Model for Parallax Camera Motion Blur. in R Gade, M Felsberg & J-K Kämäräinen (eds), Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, Proceedings, Part I.. 1 edn, Lecture Notes in Computer Science, vol. 13885 LNCS, Springer, pp. 279-296, Scandinavian Conference on Image Analysis, Lapland, Finland, 18/04/23. https://doi.org/10.1007/978-3-031-31435-3_19

Depth-Aware Image Compositing Model for Parallax Camera Motion Blur. / Torres, German F.; Kämäräinen, Joni.
Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, Proceedings, Part I.. ed. / Rikke Gade; Michael Felsberg; Joni-Kristian Kämäräinen. 1. ed. Springer, 2023. p. 279-296 (Lecture Notes in Computer Science; Vol. 13885 LNCS).

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

TY - GEN

T1 - Depth-Aware Image Compositing Model for Parallax Camera Motion Blur

AU - Torres, German F.

AU - Kämäräinen, Joni

PY - 2023

Y1 - 2023

N2 - Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent spatially varying blur. The (forward) model produces realistic motion blur from a single image, depth map, and camera trajectory. Furthermore, we utilize the ICB model, combined with a coordinate-based MLP, to learn a sharp neural representation from the blurred input. Experimental results are reported for synthetic and real examples. The results verify that the ICB forward model is computationally efficient and produces realistic blur, despite the lack of occlusion information. Additionally, our method for restoring a sharp representation proves to be a competitive approach for the deblurring task.

AB - Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent spatially varying blur. The (forward) model produces realistic motion blur from a single image, depth map, and camera trajectory. Furthermore, we utilize the ICB model, combined with a coordinate-based MLP, to learn a sharp neural representation from the blurred input. Experimental results are reported for synthetic and real examples. The results verify that the ICB forward model is computationally efficient and produces realistic blur, despite the lack of occlusion information. Additionally, our method for restoring a sharp representation proves to be a competitive approach for the deblurring task.

KW - blur formation

KW - deblurring

KW - image compositing blur

KW - neural representations

U2 - 10.1007/978-3-031-31435-3_19

DO - 10.1007/978-3-031-31435-3_19

M3 - Conference contribution

AN - SCOPUS:85161445387

SN - 9783031314346

T3 - Lecture Notes in Computer Science

SP - 279

EP - 296

BT - Image Analysis

A2 - Gade, Rikke

A2 - Felsberg, Michael

A2 - Kämäräinen, Joni-Kristian

PB - Springer

T2 - Scandinavian Conference on Image Analysis

Y2 - 18 April 2023 through 21 April 2023

ER -