{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T06:19:36Z","timestamp":1763360376297,"version":"3.45.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["ID2022-136684OB-C22","ID2022-136684OB-C22","ID2022-136684OB-C22","ID2022-136684OB-C22"],"award-info":[{"award-number":["ID2022-136684OB-C22","ID2022-136684OB-C22","ID2022-136684OB-C22","ID2022-136684OB-C22"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SMARTY","award":["101140087","101140087","101140087"],"award-info":[{"award-number":["101140087","101140087","101140087"]}]},{"name":"Universidad Carlos III"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI &amp; Soc"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid adoption of generative artificial intelligence (AI) is accelerating content creation and modification. For example, variations of a given content, be it text or images, can be created almost instantly and at a low cost. This will soon lead to the majority of text and images being created directly by AI models or by humans assisted by AI. This poses new risks; for example, AI-generated content may be used to train newer AI models and degrade their performance, or information may be lost in the transformations made by AI which could occur when the same content is processed over and over again by AI tools. An example of AI image modifications is inpainting in which an AI model completes missing fragments of an image. The incorporation of inpainting tools into photo editing programs promotes their adoption and encourages their recursive use to modify images. Inpainting can be applied recursively, starting from an image, removing some parts, applying inpainting to reconstruct the image, revising it, and then starting the inpainting process again on the reconstructed image, etc. This paper presents an empirical evaluation of recursive inpainting when using one of the most widely used image models: Stable Diffusion. The inpainting process is applied by randomly selecting a fragment of the image, reconstructing it, selecting another fragment, and repeating the process a predefined number of iterations. The images used in the experiments are taken from a publicly available art data set and correspond to different styles and historical periods. Additionally, photographs are also evaluated as a reference. The modified images are compared with the original ones by both using quantitative metrics and performing a qualitative analysis. The results show that recursive inpainting in some cases modifies the image so that it still resembles the original one while in others leads to image degeneration, so ending with a non-meaningful image. The outcome of the recursive inpainting process depends on several factors, such as the type of image, the size of the inpainting masks, and the number of iterations. The results of our evaluation illustrate how information can be lost due to successive AI transformations. The evaluation of additional models, images, and inpainting sequences is needed to confirm whether this observation is generally applicable or if it occurs only in some models and settings.<\/jats:p>","DOI":"10.1007\/s00146-025-02351-5","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:35:31Z","timestamp":1747755331000},"page":"6309-6325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Recursive InPainting (RIP): how much information is lost under recursive inferences?"],"prefix":"10.1007","volume":"40","author":[{"given":"Javier","family":"Conde","sequence":"first","affiliation":[]},{"given":"Miguel","family":"Gonzalez","sequence":"additional","affiliation":[]},{"given":"Gonzalo","family":"Mart\u00ednez","sequence":"additional","affiliation":[]},{"given":"Fernando","family":"Moral","sequence":"additional","affiliation":[]},{"given":"Elena","family":"Merino-Gomez","sequence":"additional","affiliation":[]},{"given":"Pedro","family":"Reviriego","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"2351_CR1","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, Altman S, Anadkat S et al (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"2351_CR2","doi-asserted-by":"publisher","unstructured":"Antony VN, Huang CM (2024) August. Id.8: Co-creating visual stories with generative ai. ACM Trans. Interact. Intell. Syst.\u00a014(3). https:\/\/doi.org\/10.1145\/3672277","DOI":"10.1145\/3672277"},{"key":"2351_CR3","doi-asserted-by":"crossref","unstructured":"Batley A, Glithro R et al (2024) Exploring the synergy of ai generative fill in photoshop and the creative design process utilising informal learning. In DS 131: Proceedings of the International Conference on Engineering and Product Design Education (E &PDE 2024), pp. 1\u20136","DOI":"10.35199\/EPDE.2024.1"},{"key":"2351_CR4","unstructured":"Bertrand Q, Bose AJ, Duplessis A, Jiralerspong M, Gidel G (2023) On the stability of iterative retraining of generative models on their own data. arXiv preprint arXiv:2310.00429"},{"key":"2351_CR5","unstructured":"Briesch M, Sobania D, Rothlauf F (2023) Large language models suffer from their own output: An analysis of the self-consuming training loop. arXiv preprint arXiv:2311.16822"},{"key":"2351_CR6","doi-asserted-by":"publisher","unstructured":"Cau FM, Hauptmann H, Spano LD, Tintarev N (2023) December. Effects of ai and logic-style explanations on users\u2019 decisions under different levels of uncertainty. ACM Trans. Interact. Intell. Syst.\u00a013(4). https:\/\/doi.org\/10.1145\/3588320","DOI":"10.1145\/3588320"},{"key":"2351_CR7","unstructured":"Cobbe K, Kosaraju V, Bavarian M, Chen M, Jun H, Kaiser L, Plappert M, Tworek J, Hilton J, Nakano R et al (2021) Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168"},{"issue":"1","key":"2351_CR8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA (2018) Generative adversarial networks: An overview. IEEE Signal Processing Magazine 35(1):53\u201365. https:\/\/doi.org\/10.1109\/MSP.2017.2765202","journal-title":"IEEE Signal Processing Magazine"},{"key":"2351_CR9","unstructured":"Dohmatob E, Feng Y, Yang P, Charton F, Kempe J (2024) A tale of tails: Model collapse as a change of scaling laws. arXiv preprint arXiv:2402.07043"},{"key":"2351_CR10","unstructured":"Gerstgrasser M, Schaeffer R, Dey A, Rafailov R, Sleight H, Hughes J, Korbak T, Agrawal R, Pai D, Gromov A et al (2024) Is model collapse inevitable? breaking the curse of recursion by accumulating real and synthetic data. arXiv preprint arXiv:2404.01413"},{"key":"2351_CR11","unstructured":"Guo Z, Jin R, Liu C, Huang Y, Shi D, Yu L, Liu Y, Li J, Xiong B, Xiong D et al (2023) Evaluating large language models: A comprehensive survey. arXiv preprint arXiv:2310.19736"},{"key":"2351_CR12","volume-title":"Advances in Neural Information Processing Systems","author":"M Heusel","year":"2017","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in Neural Information Processing Systems, vol 30. Curran Associates Inc"},{"key":"2351_CR13","unstructured":"Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360"},{"key":"2351_CR14","doi-asserted-by":"publisher","unstructured":"Jin Y, Wu J, Wang W, Yan Y, Jiang J, Zheng J (2023) aug. Cascading blend network for image inpainting. ACM Trans. Multimedia Comput. Commun. Appl.\u00a020(1). https:\/\/doi.org\/10.1145\/3608952","DOI":"10.1145\/3608952"},{"key":"2351_CR15","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems\u00a025"},{"key":"2351_CR16","unstructured":"Kynk\u00e4\u00e4nniemi T, Karras T, Laine S, Lehtinen J, Aila T (2019) Improved precision and recall metric for assessing generative models. Advances in Neural Information Processing Systems\u00a032"},{"key":"2351_CR17","doi-asserted-by":"crossref","unstructured":"Lugmayr A, Danelljan M, Romero A, Yu F, Timofte R, Van Gool L (2022) Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11461\u201311471","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2351_CR18","doi-asserted-by":"crossref","unstructured":"Marchi M, Soatto S, Chaudhari P, Tabuada P (2024) Heat death of generative models in closed-loop learning. arXiv preprint arXiv:2404.02325","DOI":"10.1109\/CDC56724.2024.10886816"},{"key":"2351_CR19","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez G, Watson L, Reviriego P, Hern\u00e1ndez JA, Juarez M, Sarkar R (2023) Towards understanding the interplay of generative artificial intelligence and the internet. In International Workshop on Epistemic Uncertainty in Artificial Intelligence, pp. 59\u201373. Springer","DOI":"10.1007\/978-3-031-57963-9_5"},{"issue":"0","key":"2351_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/00393630.2023.2227798","volume":"0","author":"F Moral-Andr\u00e9s","year":"2023","unstructured":"Moral-Andr\u00e9s F, Merino-G\u00f3mez E, Reviriego P, Lombardi F (2023) Can artificial intelligence reconstruct ancient mosaics? Studies in Conservation 0(0):1\u201314. https:\/\/doi.org\/10.1080\/00393630.2023.2227798","journal-title":"Studies in Conservation"},{"key":"2351_CR21","unstructured":"Naeem MF, Oh SJ, Uh Y, Choi Y, Yoo J (2020) Reliable fidelity and diversity metrics for generative models. In International Conference on Machine Learning, pp. 7176\u20137185. PMLR"},{"key":"2351_CR22","doi-asserted-by":"crossref","unstructured":"Quan W, Chen J, Liu Y, Yan DM, Wonka P (2024) Deep learning-based image and video inpainting: A survey. International Journal of Computer Vision: 1\u201334","DOI":"10.1007\/s11263-023-01977-6"},{"key":"2351_CR23","unstructured":"Ramesh A, Pavlov M, Goh G, Gray S, Voss C, Radford A, Chen M, Sutskever I (2021) Zero-shot text-to-image generation. In International conference on machine learning, pp. 8821\u20138831. Pmlr"},{"key":"2351_CR24","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022a) High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2351_CR25","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022b) High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2351_CR26","unstructured":"Sohl-Dickstein J, Weiss E, Maheswaranathan N, Ganguli S (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, pp. 2256\u20132265. PMLR"},{"key":"2351_CR27","unstructured":"Srivastava A, Rastogi A, Rao A, Shoeb AAM, Abid A, Fisch A, Brown AR, Santoro A, Gupta A, Garriga-Alonso A et al (2022) Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615"},{"key":"2351_CR28","doi-asserted-by":"crossref","unstructured":"Suvorov R, Logacheva E, Mashikhin A, Remizova A, Ashukha A, Silvestrov A, Kong N, Goka H, Park K, Lempitsky V (2022) Resolution-robust large mask in painting with fourier convolutions. In 2022 Ieee Winter Conference On Applications Of Computer Vision (Wacv 2022), pp. 3172\u20133182. IEEE COMPUTER SOC","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"2351_CR29","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F et al (2023) Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"issue":"4","key":"2351_CR30","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13(4):600\u2013612","journal-title":"IEEE transactions on image processing"},{"key":"2351_CR31","unstructured":"Wang Z, Simoncelli EP, Bovik AC (2003) Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, Volume\u00a02, pp. 1398\u20131402. Ieee"},{"key":"2351_CR32","doi-asserted-by":"crossref","unstructured":"Yang S, Chen X, Liao J (2023) Uni-paint: A unified framework for multimodal image inpainting with pretrained diffusion model. In Proceedings of the 31st ACM International Conference on Multimedia, pp. 3190\u20133199","DOI":"10.1145\/3581783.3612200"},{"key":"2351_CR33","unstructured":"Yu W, Yang K, Bai Y, Xiao T, Yao H, Rui Y (2016) Visualizing and comparing alexnet and vgg using deconvolutional layers. In Proceedings of the 33 rd International Conference on Machine Learning"},{"key":"2351_CR34","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2351_CR35","unstructured":"Zhao S, Cui J, Sheng Y, Dong Y, Liang X, Chang EI, Xu Y (2021) Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428"}],"container-title":["AI &amp; SOCIETY"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00146-025-02351-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00146-025-02351-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00146-025-02351-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T06:16:33Z","timestamp":1763360193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00146-025-02351-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2351"],"URL":"https:\/\/doi.org\/10.1007\/s00146-025-02351-5","relation":{},"ISSN":["0951-5666","1435-5655"],"issn-type":[{"type":"print","value":"0951-5666"},{"type":"electronic","value":"1435-5655"}],"subject":[],"published":{"date-parts":[[2025,5,20]]},"assertion":[{"value":"10 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}