Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation

Tsuyoshi Migita; Ayane Okada; Norikazu Takahashi

doi:10.1007/978-3-031-06381-7_3

Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation

Tsuyoshi Migita, Ayane Okada, Norikazu Takahashi

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

Abstract

When a 3D scene is captured in several 2D images, a compact description (or parameters) of the 3D scene can be estimated from the images. Such an inference is formulated as the inverse of rendering computer graphics and is important for various applications, such as object recognition, inspection, and/or VR. In the present paper, we extend a photometric stereo method in such a way as to estimate the texture of the object in addition to previous estimation of parameters describing the objects and light sources. To do so, we need a realistic minimization method, combined with a method to obtain the Jacobian of the cost function with respect to the texture. We implemented this method and verified the validity of the framework using synthetic and real-world data.

Original language	English
Title of host publication	Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers
Editors	Kazuhiko Sumi, In Seop Na, Naoshi Kaneko
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	34-48
Number of pages	15
ISBN (Print)	9783031063800
DOIs	https://doi.org/10.1007/978-3-031-06381-7_3
Publication status	Published - 2022
Event	28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022 - Virtual, Online Duration: Feb 21 2022 → Feb 22 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1578 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022
City	Virtual, Online
Period	2/21/22 → 2/22/22

Keywords

Computer graphics
Inverse rendering
Jacobian
Levenberg-Marquardt method
Superquadrics
Two-stage rendering
Uncalibrated photometric stereo

ASJC Scopus subject areas

Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-3-031-06381-7_3

Cite this

Migita, T., Okada, A., & Takahashi, N. (2022). Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation. In K. Sumi, I. S. Na, & N. Kaneko (Eds.), Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers (pp. 34-48). (Communications in Computer and Information Science; Vol. 1578 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-06381-7_3

Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation. / Migita, Tsuyoshi; Okada, Ayane; Takahashi, Norikazu.

Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers. ed. / Kazuhiko Sumi; In Seop Na; Naoshi Kaneko. Springer Science and Business Media Deutschland GmbH, 2022. p. 34-48 (Communications in Computer and Information Science; Vol. 1578 CCIS).

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

Migita, T, Okada, A & Takahashi, N 2022, Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation. in K Sumi, IS Na & N Kaneko (eds), Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers. Communications in Computer and Information Science, vol. 1578 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 34-48, 28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022, Virtual, Online, 2/21/22. https://doi.org/10.1007/978-3-031-06381-7_3

Migita T, Okada A, Takahashi N. Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation. In Sumi K, Na IS, Kaneko N, editors, Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2022. p. 34-48. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-031-06381-7_3

Migita, Tsuyoshi ; Okada, Ayane ; Takahashi, Norikazu. / Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation. Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers. editor / Kazuhiko Sumi ; In Seop Na ; Naoshi Kaneko. Springer Science and Business Media Deutschland GmbH, 2022. pp. 34-48 (Communications in Computer and Information Science).

@inproceedings{66c0f3091de14648a8ed807273988755,

title = "Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation",

abstract = "When a 3D scene is captured in several 2D images, a compact description (or parameters) of the 3D scene can be estimated from the images. Such an inference is formulated as the inverse of rendering computer graphics and is important for various applications, such as object recognition, inspection, and/or VR. In the present paper, we extend a photometric stereo method in such a way as to estimate the texture of the object in addition to previous estimation of parameters describing the objects and light sources. To do so, we need a realistic minimization method, combined with a method to obtain the Jacobian of the cost function with respect to the texture. We implemented this method and verified the validity of the framework using synthetic and real-world data.",

keywords = "Computer graphics, Inverse rendering, Jacobian, Levenberg-Marquardt method, Superquadrics, Two-stage rendering, Uncalibrated photometric stereo",

author = "Tsuyoshi Migita and Ayane Okada and Norikazu Takahashi",

note = "Funding Information: Supported by JSPS KAKENHI Grant Number 20K11866. Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022 ; Conference date: 21-02-2022 Through 22-02-2022",

year = "2022",

doi = "10.1007/978-3-031-06381-7_3",

language = "English",

isbn = "9783031063800",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "34--48",

editor = "Kazuhiko Sumi and Na, {In Seop} and Naoshi Kaneko",

booktitle = "Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers",

address = "Germany",

}

TY - GEN

T1 - Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation

AU - Migita, Tsuyoshi

AU - Okada, Ayane

AU - Takahashi, Norikazu

PY - 2022

Y1 - 2022

N2 - When a 3D scene is captured in several 2D images, a compact description (or parameters) of the 3D scene can be estimated from the images. Such an inference is formulated as the inverse of rendering computer graphics and is important for various applications, such as object recognition, inspection, and/or VR. In the present paper, we extend a photometric stereo method in such a way as to estimate the texture of the object in addition to previous estimation of parameters describing the objects and light sources. To do so, we need a realistic minimization method, combined with a method to obtain the Jacobian of the cost function with respect to the texture. We implemented this method and verified the validity of the framework using synthetic and real-world data.

AB - When a 3D scene is captured in several 2D images, a compact description (or parameters) of the 3D scene can be estimated from the images. Such an inference is formulated as the inverse of rendering computer graphics and is important for various applications, such as object recognition, inspection, and/or VR. In the present paper, we extend a photometric stereo method in such a way as to estimate the texture of the object in addition to previous estimation of parameters describing the objects and light sources. To do so, we need a realistic minimization method, combined with a method to obtain the Jacobian of the cost function with respect to the texture. We implemented this method and verified the validity of the framework using synthetic and real-world data.

KW - Computer graphics

KW - Inverse rendering

KW - Jacobian

KW - Levenberg-Marquardt method

KW - Superquadrics

KW - Two-stage rendering

KW - Uncalibrated photometric stereo

UR - http://www.scopus.com/inward/record.url?scp=85131131358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85131131358&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-06381-7_3

DO - 10.1007/978-3-031-06381-7_3

M3 - Conference contribution

AN - SCOPUS:85131131358

SN - 9783031063800

T3 - Communications in Computer and Information Science

SP - 34

EP - 48

BT - Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers

A2 - Sumi, Kazuhiko

A2 - Na, In Seop

A2 - Kaneko, Naoshi

PB - Springer Science and Business Media Deutschland GmbH

T2 - 28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022

Y2 - 21 February 2022 through 22 February 2022

ER -