Originalidad de obras de arte digital generadas por IA: Una revisión sistemática de la literatura
DOI:
https://doi.org/10.15649/2346030X.4582Palabras clave:
inteligencia artificial generativa, ia generativa, originalidad, obras de arte digital, autenticidadResumen
Este artículo de Revisión Sistemática de la Literatura tuvo como objetivo resumir la información sobre la originalidad de obras de arte digital creadas por IA generativa, para ello, se realizó una búsqueda en las bases de datos: IEEE Xplore, Scopus, ScienceDirect y SpringerLink, encontrándose, tras aplicar criterios de inclusión y exclusión, un total de 51 artículos de investigación. Los principales hallazgos fueron: los aportes más destacados de la IA generativa en el arte digital fueron la eficiencia, automatización e innovación artística, con una valoración del 21.88%; las técnicas más empleadas para la creación de obras digitales fueron las Redes Generativas Antagónicas y sus variantes, con una valoración del 32.14%; los desafíos éticos más relevantes se relacionan con los sesgos en los datos y la discriminación, alcanzando un 32%; los datos de entrenamiento más comunes fueron imágenes etiquetadas y bases públicas, con una valoración del 32.5%; y finalmente, los aspectos clave para evaluar la originalidad en estas obras fueron la calidad y diversidad visual, con una valoración del 30%. En conclusión, la IA generativa es clave para la innovación en el arte digital, pero su uso debe gestionarse con precaución debido a los sesgos y desafíos éticos que conlleva.
Referencias
[1] S. Bengesi, H. El-Sayed, M. K. Sarker, Y. Houkpati, J. Irungu, y T. Oladunni, "Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers", IEEE Access, vol. 12, pp. 69812-69837, may 2024, doi: 10.1109/ACCESS.2024.3397775.
[2] Z. W. Wu, H. Qu, y K. Zhang, "A Survey of Recent Practice of Artificial Life in Visual Art", Artif. Life, vol. 30, n.o 1, pp. 106-135, feb. 2024, doi: 10.1162/artl_a_00433.
[3] M. Gao y P. Pu, "Generative Adversarial Network-Based Experience Design for Visual Communication: An Innovative Exploration in Digital Media Arts", IEEE Access, vol. 12, pp. 92035-92042, jul. 2024, doi: 10.1109/ACCESS.2024.3419212.
[4] B. Kitchenham, P. Brereton, D. Budgen, M. Turner, J. Bailey, y S. Linkman, "Systematic literature reviews in software engineering-A systematic literature review", Inf. Softw. Technol., vol. 51, pp. 7-15, ene. 2009, doi: 10.1016/j.infsof.2008.09.009.
[5] L. Banh y G. Strobel, "Generative artificial intelligence", Electron. Mark., vol. 33, n.o 1, p. 63, dic. 2023, doi: 10.1007/s12525-023-00680-1.
[6] Y. Wang, Y. Pan, M. Yan, Z. Su, y T. H. Luan, "A Survey on ChatGPT: AI–Generated Contents, Challenges, and Solutions", IEEE Open J. Comput. Soc., vol. 4, pp. 280-302, oct. 2023, doi: 10.1109/OJCS.2023.3300321.
[7] A. Tian y L. Lu, "Attentional Generative Adversarial Networks With Representativeness and Diversity for Generating Text to Realistic Image", IEEE Access, vol. 8, pp. 9587-9596, ene. 2020, doi: 10.1109/ACCESS.2020.2964946.
[8] K. Tatar et al., "A Shift in Artistic Practices through Artificial Intelligence", Leonardo, vol. 57, n.o 3, pp. 293-297, 2024, doi: 10.1162/leon_a_02523.
[9] N. Anantrasirichai y D. Bull, "Artificial intelligence in the creative industries: a review", Artif. Intell. Rev., vol. 55, n.o 1, pp. 589-656, jul. 2022, doi: 10.1007/s10462-021-10039-7.
[10] T. Wu et al., "Recent advances in 3D Gaussian splatting", Comput. Vis. Media, vol. 10, n.o 4, pp. 613-642, ago. 2024, doi: 10.1007/s41095-024-0436-y.
[11] R. West, A. Burbano, y M. Tromble, "Ai, arts & design: Questioning learning machines", Artnodes, vol. 2020, n.o 26, pp. 1-9, jul. 2020, doi: 10.7238/a.v0i26.3368.
[12] C. Chen, "Study on the Innovative Development of Digital Media Art in the Context of Artificial Intelligence", Comput. Intell. Neurosci., vol. 2022, ago. 2022, doi: 10.1155/2022/1004204.
[13] Y. Shen y F. Yu, "The Influence of Artificial Intelligence on Art Design in the Digital Age", Sci. Program., vol. 2021, dic. 2021, doi: 10.1155/2021/4838957.
[14] M. P. Schofield, "Camera Phantasma: Reframing virtual photographies in the age of AI", Convergence, vol. 30, n.o 2, pp. 687-709, dic. 2023, doi: 10.1177/13548565231220314.
[15] I. Kalpokas, "Work of art in the Age of Its AI Reproduction", Philos. Soc. Crit., jun. 2023, doi: 10.1177/01914537231184490.
[16] Y. Lyu, X. Wang, R. Lin, y J. Wu, "Communication in Human–AI Co-Creation: Perceptual Analysis of Paintings Generated by Text-to-Image System", Appl. Sci. Switz., vol. 12, n.o 22, nov. 2022, doi: 10.3390/app122211312.
[17] M. Baas, "Artificial Intelligence and the question of creativity: Art, data and the sociocultural archive of AI-imaginations", Eur. J. Cult. Stud., vol. 27, n.o 4, pp. 788-795, may 2024, doi: 10.1177/13675494241246640.
[18] R. Latikka, J. Bergdahl, N. Savela, y A. Oksanen, "AI as an Artist? A Two-Wave Survey Study on Attitudes Toward Using Artificial Intelligence in Art", Poetics, vol. 101, nov. 2023, doi: 10.1016/j.poetic.2023.101839.
[19] K. Millet, F. Buehler, G. Du, y M. Kokkoris, "Defending humankind: Anthropocentric bias in the appreciation of AI art", Comput. Hum. Behav., vol. 143, p. 107707, feb. 2023, doi: 10.1016/j.chb.2023.107707.
[20] A. Bandi, P. V. S. R. Adapa, y Y. E. V. P. K. Kuchi, "The Power of Generative AI: A Review of Requirements, Models, Input–Output Formats, Evaluation Metrics, and Challenges", Future Internet, vol. 15, n.o 8, Art. n.o 8, jul. 2023, doi: 10.3390/fi15080260.
[21] A. Aggarwal, M. Mittal, y G. Battineni, "Generative adversarial network: An overview of theory and applications", Int. J. Inf. Manag. Data Insights, vol. 1, n.o 1, p. 100004, abr. 2021, doi: 10.1016/j.jjimei.2020.100004.
[22] Y. Sun, Y. Lyu, P.-H. Lin, y R. Lin, "Comparison of Cognitive Differences of Artworks between Artist and Artistic Style Transfer", Appl. Sci. Switz., vol. 12, n.o 11, may 2022, doi: 10.3390/app12115525.
[23] K. M. Jang et al., "Place identity: a generative AI’s perspective", Humanit. Soc. Sci. Commun., vol. 11, n.o 1, sep. 2024, doi: 10.1057/s41599-024-03645-7.
[24] S. Göring, R. R. Ramachandra Rao, R. Merten, y A. Raake, "Analysis of Appeal for Realistic AI-Generated Photos", IEEE Access, vol. 11, pp. 38999-39012, abr. 2023, doi: 10.1109/ACCESS.2023.3267968.
[25] G. Devsana, K. Kumar, S. R, y S. T, "Automatic Creation of Quality Images from Text using Multiple Generative Adversial Network", Procedia Comput. Sci., vol. 230, pp. 955-963, ene. 2023, doi: 10.1016/j.procs.2023.12.135.
[26] G. Castellano y G. Vessio, "A Deep Learning Approach to Clustering Visual Arts", Int. J. Comput. Vis., vol. 130, n.o 11, pp. 2590-2605, ago. 2022, doi: 10.1007/s11263-022-01664-y.
[27] H. Pflüger, "A language to analyze, describe, and explore collections of visual art", Vis. Comput. Ind. Biomed. Art, vol. 4, n.o 1, p. 5, mar. 2021, doi: 10.1186/s42492-021-00071-3.
[28] D. B. Ebaid, M. M. Madbouly, y A. A. El-Zoghabi, "Bi-directional Image–Text Matching Deep Learning-Based Approaches: Concepts, Methodologies, Benchmarks and Challenges", Int. J. Comput. Intell. Syst., vol. 16, n.o 1, p. 81, may 2023, doi: 10.1007/s44196-023-00260-3.
[29] G. Castellano y G. Vessio, "Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview", Neural Comput. Appl., vol. 33, n.o 19, pp. 12263-12282, abr. 2021, doi: 10.1007/s00521-021-05893-z.
[30] K. Psychogyios, H. C. Leligou, F. Melissari, S. Bourou, Z. Anastasakis, y T. Zahariadis, "SAMStyler: Enhancing Visual Creativity With Neural Style Transfer and Segment Anything Model (SAM)", IEEE Access, vol. 11, pp. 100256-100267, sep. 2023, doi: 10.1109/ACCESS.2023.3315235.
[31] J. Oppenlaender, "A taxonomy of prompt modifiers for text-to-image generation", Behav. Inf. Technol., nov. 2023, doi: 10.1080/0144929X.2023.2286532.
[32] J. O’Meara y C. Murphy, "Aberrant AI creations: co-creating surrealist body horror using the DALL-E Mini text-to-image generator", Convergence, vol. 29, n.o 4, pp. 1070-1096, jul. 2023, doi: 10.1177/13548565231185865.
[33] Q. Wang, C. Guo, H.-N. Dai, y P. Li, "Stroke-GAN Painter: Learning to paint artworks using stroke-style generative adversarial networks", Comput. Vis. Media, vol. 9, n.o 4, pp. 787-806, dic. 2023, doi: 10.1007/s41095-022-0287-3.
[34] S. Sai, R. Sai, y V. Chamola, "Generative AI for Industry 5.0: Analyzing the impact of ChatGPT, DALLE, and Other Models", IEEE Open J. Commun. Soc., pp. 1-1, ene. 2024, doi: 10.1109/OJCOMS.2024.3400161.
[35] L. Wang, W. Chen, W. Yang, F. Bi, y F. R. Yu, "A State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks", IEEE Access, vol. 8, pp. 63514-63537, abr. 2020, doi: 10.1109/ACCESS.2020.2982224.
[36] B. Kang, S. Tripathi, y T. Q. Nguyen, "Generating images in compressed domain using generative adversarial networks", IEEE Access, vol. 8, pp. 180977-180991, oct. 2020, doi: 10.1109/ACCESS.2020.3027800.
[37] B. Liu, J. Lv, X. Fan, J. Luo, y T. Zou, "Application of an Improved DCGAN for Image Generation", Mob. Inf. Syst., vol. 2022, jul. 2022, doi: 10.1155/2022/9005552.
[38] K. Ko, T. Yeom, y M. Lee, "SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains", Neural Netw., vol. 162, pp. 330-339, mar. 2023, doi: 10.1016/j.neunet.2023.02.042.
[39] L. Ren y Y. Song, "AOGAN: A generative adversarial network for screen space ambient occlusion", Comput. Vis. Media, vol. 8, n.o 3, pp. 483-494, sep. 2022, doi: 10.1007/s41095-021-0248-2.
[40] Z. Yang, Y. Chen, Z. Le, y Y. Ma, "GANFuse: a novel multi-exposure image fusion method based on generative adversarial networks", Neural Comput. Appl., vol. 33, n.o 11, pp. 6133-6145, nov. 2020, doi: 10.1007/s00521-020-05387-4.
[41] D. Park, H. Na, y D. Choi, "Performance Comparison and Visualization of AI-Generated-Image Detection Methods", IEEE Access, vol. 12, pp. 62609-62627, may 2024, doi: 10.1109/ACCESS.2024.3394250.
[42] J. J. Bird y A. Lotfi, "CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images", IEEE Access, vol. 12, pp. 15642-15650, feb. 2024, doi: 10.1109/ACCESS.2024.3356122.
[43] S. K. Lee y Y. R. Koo, "Proposal of a Facilitation and Process Model for Enhancing Creativity in Co-design Workshops with Generative AI: The Use of ChatGPT", 31 de mayo de 2024. doi: 10.15187/adr.2024.05.37.2.249.
[44] F.-L. Chen et al., "VLP: A Survey on Vision-language Pre-training", Mach. Intell. Res., vol. 20, n.o 1, pp. 38-56, feb. 2023, doi: 10.1007/s11633-022-1369-5.
[45] J. Xu, M. Yuan, D.-M. Yan, y T. Wu, "Deep unfolding multi-scale regularizer network for image denoising", Comput. Vis. Media, vol. 9, n.o 2, pp. 335-350, jun. 2023, doi: 10.1007/s41095-022-0277-5.
[46] K. Zhang et al., "Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis", Mach. Intell. Res., vol. 20, n.o 6, pp. 822-836, dic. 2023, doi: 10.1007/s11633-023-1466-0.
[47] P. Li, D. Zhang, L. Zhao, D. Xu, y D. Lu, "Style Permutation for Diversified Arbitrary Style Transfer", IEEE Access, vol. 8, pp. 199147-199158, nov. 2020, doi: 10.1109/ACCESS.2020.3034653.
[48] H. Ramadan, C. Lachqar, y H. Tairi, "A survey of recent interactive image segmentation methods", Comput. Vis. Media, vol. 6, n.o 4, pp. 355-384, dic. 2020, doi: 10.1007/s41095-020-0177-5.
[49] E. J. López-Ortiz, M. Perea-Trigo, L. M. Soria-Morillo, F. Sancho-Caparrini, y J. J. Vegas-Olmos, "Exploring deep echo state networks for image classification: a multi-reservoir approach", Neural Comput. Appl., vol. 36, n.o 20, pp. 11901-11918, abr. 2024, doi: 10.1007/s00521-024-09656-4.
[50] T. Qin, S. Tu, y L. Xu, "IA-NGM: A bidirectional learning method for neural graph matching with feature fusion", Mach. Learn., vol. 113, n.o 4, pp. 1743-1769, nov. 2022, doi: 10.1007/s10994-022-06255-z.
[51] E. M. Kuehn, "A new business model in the fine arts realm based on NFT certificates and pearl codes", Digit. Bus., vol. 4, n.o 2, jun. 2024, doi: 10.1016/j.digbus.2024.100079.
[52] S. S. Gill y R. Kaur, "ChatGPT: Vision and challenges", Internet Things Cyber-Phys. Syst., vol. 3, pp. 262-271, may 2023, doi: 10.1016/j.iotcps.2023.05.004.
Descargas
Publicado
Cómo citar
Descargas
Número
Sección
Licencia
Derechos de autor 2025 AiBi Revista de Investigación, Administración e Ingeniería
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
La revista ofrece acceso abierto bajo una Licencia Creative Commons Attibution License
Esta obra está bajo una licencia Creative Commons Attribution (CC BY 4.0).
