Understanding Compositional Structures in Art Historical Images Using Pose and Gaze Priors

Madhu P, Marquart T, Kosti RV, Bell P, Maier A, Christlein V (2020)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2020

Publisher: Springer, Cham

Series: Lecture Notes in Computer Science

City/Town: Switzerland

Book Volume: 12536

Pages Range: 109-125

Conference Proceedings Title: Computer Vision – ECCV 2020 Workshops. ECCV 2020

Event location: Glasgow

ISBN: 978-3-030-66095-6

URI: https://link.springer.com/chapter/10.1007/978-3-030-66096-3_9

DOI: 10.1007/978-3-030-66096-3_9

Abstract

Image compositions as a tool for analysis of artworks is of extreme significance for art historians. These compositions are useful in analyzing the interactions in an image to study artists and their artworks. Max Imdahl in his work called Ikonik, along with other prominent art historians of the 20th" role="presentation" style="display: inline-table; line-height: normal; letter-spacing: normal; word-spacing: normal; overflow-wrap: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border-width: 0px; border-style: initial; position: relative;">thth century, underlined the aesthetic and semantic importance of the structural composition of an image. Understanding underlying compositional structures within images is challenging and a time consuming task. Generating these structures automatically using computer vision techniques (1) can help art historians towards their sophisticated analysis by saving lot of time; providing an overview and access to huge image repositories and (2) also provide an important step towards an understanding of man made imagery by machines. In this work, we attempt to automate this process using the existing state of the art machine learning techniques, without involving any form of training. Our approach, inspired by Max Imdahl’s pioneering work, focuses on two central themes of image composition: (a) detection of action regions and action lines of the artwork; and (b) pose-based segmentation of foreground and background. Currently, our approach works for artworks comprising of protagonists (persons) in an image. In order to validate our approach qualitatively and quantitatively, we conduct a user study involving experts and non-experts. The outcome of the study highly correlates with our approach and also demonstrates its domain-agnostic capability. We have open-sourced the code: https://github.com/image-compostion-canvas-group/image-compostion-canvas

Authors with CRIS profile

Related research project(s)

How to cite

APA:

Madhu, P., Marquart, T., Kosti, R.V., Bell, P., Maier, A., & Christlein, V. (2020). Understanding Compositional Structures in Art Historical Images Using Pose and Gaze Priors. In Andrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm (Eds.), Computer Vision – ECCV 2020 Workshops. ECCV 2020 (pp. 109-125). Glasgow, GB: Switzerland: Springer, Cham.

MLA:

Madhu, Prathmesh, et al. "Understanding Compositional Structures in Art Historical Images Using Pose and Gaze Priors." Proceedings of the ECCV 2020, Glasgow Ed. Andrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm, Switzerland: Springer, Cham, 2020. 109-125.

BibTeX: Download