Novel Paradigm of Cameraless Photography: Methodology of AI-generated photographs

After the modernist period of chemigram cameraless practices, photography in the digital and post-photography moment raised some methods such as found, altered, distorted, which are called appropriation. These approaches are connected and progressively affected by experimental photography, which is also called hybrid practices using analog and digital mediums. These neo-avant-garde moments are now becoming more cameraless and not witnessed by light but codes. Currently, further AI-generated photography and its background machine learning system GANs (Generative Adversarial Networks), StyleGAN and StyleGan2 create real portraits. The main issue to be addressed here is how to read these photographs, which are more analogous to reality than ever before. In this study, Deleuze’s rhizomatic approach will be considered to examine the issue. The rhizomatic philosophical concept has no centre, which loses a point/channel of desire (deterritorialization) only to start along a new path like a rhizome’s spread (reterritorialization). Never-ending stream of images by GANs has a very similar structure with the body without organs/images flow and the organization, but with consistency. This process of interconnectedness and extinction shows that each portrait created is linked in a rhizomatic way. Some questions will also be reconsidered in this context: Could we still mention photography, or are these just images? In both situations, what are their specificity and structure? How could it be studied with a novel methodology and paradigm?

Content

Author and article information

Contributors

Ozan Yavuz

Conference

Publication date: July 2021

Publication date (Print): July 2021

Pages: 207-213

Affiliations

[0001]Middle East Technical University

Department of Music and Fine Arts, 06800, Ankara, Turkey

Article

DOI: 10.14236/ewic/EVA2021.35

SO-VID: 27c7f1e2-170b-441c-9b65-7f5717bc9c2f

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Conference name: Proceedings of EVA London 2021

Conference acronym: EVA 2021

Conference number:

Conference location: London

Conference date: 5th July – 9th July 2021

Conference sponsor: Electronic Workshops in Computing (eWiC)

Conference theme: AI and the Arts: Artificial Imagination

History

Product

1477-9358 BCS Learning & Development

Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/EVA2021.35

Self URI (journal page): https://ewic.bcs.org/

REFERENCES

Brent Adkins. (2015) Deleuze and Guattari’s A Thousand Plateaus: A Critical Introduction and Guide. Edinburgh University Press, Edinburgh.
Martin Barnes. (2012) Shadow Catchers: Cameraless Photography. Perseus Distribution Services, London.
Roland Barthes, (1977) [1967] ‘Death of the Author,’ Image, Music and Text, transl. Stephen Heath. Hill & Wang, New York.
Roland Barthes. (1981). Camera lucida: Reflections on photography (1st American ed.). Hill and Wang.
Baudrillard, (1994) Simulacra and Simulation, Sheila Faria Glaser (trans.), University of Michigan Press, Ann Arbor.
Geoffrey Batchen. (2001) “Carnal Knowledge.” Art Journal 60:1, 21-23. Print.
Geoffrey Batchen. (2016) Emanations: the art of the cameraless photograph. DelMonico Books, Munich London New York.
Pierre Cordier. (1982) Chemigram: A New Approach to Lensless Photography. Leonardo, 15(4), 262-268. [Cross Ref].
Jonathan Crary. (1992). Techniques of the observer : on vision and modernity in the nineteenth century. MIT Press, Cambridge [Mass.]
Gilles Deleuze and Félix Guattari. (1980). A Thousand Plateaus. Trans. Brian Massumi. London and New York: Continuum, 2004. Vol. 2 of Capitalism and Schizophrenia. 2 vols. 1972-1980. Trans. of Mille Plateaux. Les Editions de Minuit, Paris.
Michel Foucault. (1977) "What Is an Author" Language, Counter-Memory, Practice: Selected Essays and Interviews. Ed. Donald F. Bouchard. Cornell University Press, Ithaca, NY, 113-38.
Michel Foucault. (2011) "Nietzsche, Soybilim, Tarih", içinde Felsefe Sahnesi, çev. Işık Ergüden, Ayrıntı Yayınları, İstanbul.
Ian Goodfellow; Jean Pouget-Abadie; Mehdi Mirza; Bing Xu; David Warde-Farley; Sherjil Ozair; Aaron Courville; Yoshua Bengio (2014). Generative Adversarial Networks (PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680.
G. Jäger (2005) ‘Concrete Photography’ In: Beate Reese, Jager Gottfried, and Rolf H. Krauss (ed.) Concrete Photography = Konkrete Fotografie. Bielefeld: Kerber Verlag. pp.16-26.
T. Karras, S. Laine, & T. Aila (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4401-4410).
T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, & T. Aila (2020). Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8110-8119).
Rosalind Krauss. (1977) Notes on the Index: Seventies Art in America. October 3, pp. 68-81.
Rolf H. Krauss (2005) ‘A Small History of Concrete Photography’ In: Beate Reese, Jager Gottfried, and Rolf H Krauss (ed.) Concrete Photography = Konkrete Fotografie. Bielefeld: Kerber Verla
W. Li, P. Zhang, L. Zhang, Q. Huang, X. He, S. Lyu, & J. Gao (2019). Object-driven text-to-image synthesis via adversarial training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12174-12182).
J.-F. Lyotard, 1984 [1979], The Postmodern Condition: A Report on Knowledge, Geoff Bennington and Brian Massumi (trans.), University of Minnesota Press, Minneapolis.
Skekh Mounuddin. (2019) The Political Twitterspace in India. Springer, Switzerland.
Martin Parr and Gerry Badger. (2014) The Photobook: A History, volume I. Phaidon Press Limited, London.
T. Qiao, J. Zhang, D. Xu, & D. Tao (2019). Mirrorgan: Learning text-to-image generation by redescription. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1505-1514).
T. R. Shaham, T. Dekel, & T. Michaeli (2019). Singan: Learning a generative model from a single natural image. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4570-4580).
Nigel Warburton. (2011) HackelBury fine art – Pierre Cordier. Available at: http://www.hackelbury.co.uk/artists/cordier/cordier.html (Accessed: 20 October 2016). (Cited from Samara Knight, Camera-Less Photography: Can It Be Considered Photography?, University for the Creative Arts, BA (Hons) Photography Thesis, UK.

Comments

Comment on this article

[1] Brent Adkins. (2015) Deleuze and Guattari’s A Thousand Plateaus: A Critical Introduction and Guide. Edinburgh University Press, Edinburgh.

[2] Martin Barnes. (2012) Shadow Catchers: Cameraless Photography. Perseus Distribution Services, London.

[3] Roland Barthes, (1977) [1967] ‘Death of the Author,’ Image, Music and Text, transl. Stephen Heath. Hill & Wang, New York.

[4] Roland Barthes. (1981). Camera lucida: Reflections on photography (1st American ed.). Hill and Wang.

[5] Baudrillard, (1994) Simulacra and Simulation, Sheila Faria Glaser (trans.), University of Michigan Press, Ann Arbor.

[6] Geoffrey Batchen. (2001) “Carnal Knowledge.” Art Journal 60:1, 21-23. Print.

[7] Geoffrey Batchen. (2016) Emanations: the art of the cameraless photograph. DelMonico Books, Munich London New York.

[8] Pierre Cordier. (1982) Chemigram: A New Approach to Lensless Photography. Leonardo, 15(4), 262-268. [Cross Ref].

[9] Jonathan Crary. (1992). Techniques of the observer : on vision and modernity in the nineteenth century. MIT Press, Cambridge [Mass.]

[10] Gilles Deleuze and Félix Guattari. (1980). A Thousand Plateaus. Trans. Brian Massumi. London and New York: Continuum, 2004. Vol. 2 of Capitalism and Schizophrenia. 2 vols. 1972-1980. Trans. of Mille Plateaux. Les Editions de Minuit, Paris.

[11] Michel Foucault. (1977) "What Is an Author" Language, Counter-Memory, Practice: Selected Essays and Interviews. Ed. Donald F. Bouchard. Cornell University Press, Ithaca, NY, 113-38.

[12] Michel Foucault. (2011) "Nietzsche, Soybilim, Tarih", içinde Felsefe Sahnesi, çev. Işık Ergüden, Ayrıntı Yayınları, İstanbul.

[13] Ian Goodfellow; Jean Pouget-Abadie; Mehdi Mirza; Bing Xu; David Warde-Farley; Sherjil Ozair; Aaron Courville; Yoshua Bengio (2014). Generative Adversarial Networks (PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680.

[14] G. Jäger (2005) ‘Concrete Photography’ In: Beate Reese, Jager Gottfried, and Rolf H. Krauss (ed.) Concrete Photography = Konkrete Fotografie. Bielefeld: Kerber Verlag. pp.16-26.

[15] T. Karras, S. Laine, & T. Aila (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4401-4410).

[16] T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, & T. Aila (2020). Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8110-8119).

[17] Rosalind Krauss. (1977) Notes on the Index: Seventies Art in America. October 3, pp. 68-81.

[18] Rolf H. Krauss (2005) ‘A Small History of Concrete Photography’ In: Beate Reese, Jager Gottfried, and Rolf H Krauss (ed.) Concrete Photography = Konkrete Fotografie. Bielefeld: Kerber Verla

[19] W. Li, P. Zhang, L. Zhang, Q. Huang, X. He, S. Lyu, & J. Gao (2019). Object-driven text-to-image synthesis via adversarial training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12174-12182).

[20] J.-F. Lyotard, 1984 [1979], The Postmodern Condition: A Report on Knowledge, Geoff Bennington and Brian Massumi (trans.), University of Minnesota Press, Minneapolis.

[21] Skekh Mounuddin. (2019) The Political Twitterspace in India. Springer, Switzerland.

[22] Martin Parr and Gerry Badger. (2014) The Photobook: A History, volume I. Phaidon Press Limited, London.

[23] T. Qiao, J. Zhang, D. Xu, & D. Tao (2019). Mirrorgan: Learning text-to-image generation by redescription. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1505-1514).

[24] T. R. Shaham, T. Dekel, & T. Michaeli (2019). Singan: Learning a generative model from a single natural image. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4570-4580).

[25] Nigel Warburton. (2011) HackelBury fine art – Pierre Cordier. Available at: http://www.hackelbury.co.uk/artists/cordier/cordier.html (Accessed: 20 October 2016). (Cited from Samara Knight, Camera-Less Photography: Can It Be Considered Photography?, University for the Creative Arts, BA (Hons) Photography Thesis, UK.

Studying business & IT? Drive your professional career forwards with BCS books - for a 20% discount click here: shop.bcs.org