Transforming Pixels into a Masterpiece: AI-Powered Art Restoration using a Novel Distributed Denoising CNN (DDCNN)
Abstract: Art restoration is crucial for preserving cultural heritage, but traditional methods have limitations in faithfully reproducing original artworks while addressing issues like fading, staining, and damage. We present an innovative approach using deep learning, specifically Convolutional Neural Networks (CNNs), and Computer Vision techniques to revolutionize art restoration. We start by creating a diverse dataset of deteriorated art images with various distortions and degradation levels. This dataset trains a Distributed Denoising CNN (DDCNN) to remove distortions while preserving intricate details. Our method is adaptable to different distortion types and levels, making it suitable for various deteriorated artworks, including paintings, sketches, and photographs. Extensive experiments demonstrate our approach's efficiency and effectiveness compared to other Denoising CNN models. We achieve a substantial reduction in distortion, transforming deteriorated artworks into masterpieces. Quantitative evaluations confirm our method's superiority over traditional techniques, reshaping the art restoration field and preserving cultural heritage. In summary, our paper introduces an AI-powered solution that combines Computer Vision and deep learning with DDCNN to restore artworks accurately, overcoming limitations and paving the way for future advancements in art restoration.
- Andrea C Ash “Beyond Boundaries of Space & Time: Transmigrations in Contemporary Art”, 2011 URL: https://api.semanticscholar.org/CorpusID:129140122
- S. Kolay “Cultural Heritage Preservation of Traditional Indian Art through Virtual New-media” In Procedia - Social and Behavioral Sciences 225 Elsevier BV, 2016, pp. 309–320 DOI: 10.1016/j.sbspro.2016.06.030.
- “Art in the Global Present”, 2014 URL: https://api.semanticscholar.org/CorpusID:189365760
- “Indian Paintings: An Analysis of Geographical and Chronological Context” In Asian Journal of Social Sciences and Legal Studies Universe Publishing Group - UniversePG, 2021, pp. 75–84 DOI: 10.34104/ajssls.021.075084.
- Peter Arguimbau “The artist returns to art restoration”, 1996 URL: https://api.semanticscholar.org/CorpusID:193406453
- Giancarlo Lanterna “New methods and techniques for artistic works restoration in the Opificio delle Pietre Dure” In Conservation Science in Cultural Heritage 1, 2001, pp. 55–66 URL: https://api.semanticscholar.org/CorpusID:190973714
- E.L. Spratt “Computers and art in the age of machine learning” In XRDS: Crossroads, The ACM Magazine for Students 24.3, Association for Computing Machinery (ACM, 2018, pp. 8–20 DOI: 10.1145/3186697.
- “Wall Painting Reconstruction Using a Genetic Algorithm” In Journal on Computing and Cultural Heritage 11.1, Association for Computing Machinery (ACM, 2017, pp. 1–17 DOI: 10.1145/3084547.
- “Deep Learning for Image Denoising: A Survey” In Advances in Intelligent Systems and Computing Springer Singapore, 2019, pp. 563–572 DOI: 10.1007/978-981-13-5841-8˙59.
- J.S. Goussous “Artificial Intelligence-based Restoration: The Case of Petra” In Civil Engineering and Architecture 8.6 Horizon Research Publishing Co., Ltd, 2020, pp. 1350–1358 DOI: 10.13189/cea.2020.080618.
- “Understanding and Creating Art with AI: Review and Outlook” In ACM Transactions on Multimedia Computing, Communications, and Applications 18.2, Association for Computing Machinery (ACM, pp. 1–22 DOI: 10.1145/3475799.
- Z. Zou, P. Zhao and X. Zhao “Virtual restoration of the colored paintings on weathered beams in the Forbidden City using multiple deep learning algorithms” In Advanced Engineering Informatics 50 Elsevier BV, 2021, pp. 101421 DOI: 10.1016/j.aei.2021.101421.
- B. Cornelis “Crack detection and inpainting for virtual restoration of paintings: The case of the Ghent Altarpiece” In Signal Processing 93.3 Elsevier BV, 2013, pp. 605–619 DOI: 10.1016/j.sigpro.2012.07.022.
- A. Criminisi, P. Perez and K. Toyama “Region Filling and Object Removal by Exemplar-Based Image Inpainting” In Institute of Electrical and Electronics Engineers (IEEE 13.9, 2004, pp. 1200–1212 DOI: 10.1109/tip.2004.833105.
- S.-C. Pei, Y.-C. Zeng and C.-H. Chang “Virtual Restoration of Ancient Chinese Paintings Using Color Contrast Enhancement and Lacuna Texture Synthesis” In IEEE Transactions on Image Processing 13.3 Institute of ElectricalElectronics Engineers (IEEE, 2004, pp. 416–429 DOI: 10.1109/tip.2003.821347.
- “Image Reconstruction is a New Frontier of Machine Learning” In IEEE Transactions on Medical Imaging 37.6, 2018, pp. 1289–1296 DOI: 10.1109/TMI.2018.2833635
- “Deep Learning and the Information Bottleneck Principle” In CoRR abs/1503.02406, 2015 arXiv: http://arxiv.org/abs/1503.02406
- Shreyasi Ghose, Nishi Singh and Prabhishek Singh “Image Denoising using Deep Learning: Convolutional Neural Network” In 2020 10th International Conference on Cloud Computing, Data Science and Engineering (Confluence), 2020, pp. 511–517 DOI: 10.1109/Confluence47617.2020.9057895
- Edoardo Peretti “State of the Art on: Deep Image Denoising”, 2020 URL: https://api.semanticscholar.org/CorpusID:215747454
- “A generative adversarial network for image denoising” In Multimedia Tools and Applications 79 Springer ScienceBusiness Media LLC, 2019, pp. 23–24 DOI: 10.1007/s11042-019-7556-x.
- “Recent Study on Image Denoising using Deep CNN Techniques” In 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS) 1, 2021, pp. 1838–1843 URL: https://api.semanticscholar.org/CorpusID:235340483
- Z. Liu, W.Q. Yan and M.L. Yang “Image denoising based on a CNN model” In 2018 4th International Conference on Control, Automation and Robotics (ICCAR IEEE, Apr, 2018 DOI: 10.1109/iccar.2018.8384706.
- “A Comprehensive Review of Deep Learning-Based Real-World Image Restoration” In IEEE Access 11 Institute of ElectricalElectronics Engineers (IEEE, 2023, pp. 21049–21067 DOI: 10.1109/access.2023.3250616.
- K. Zhang, W. Zuo and L. Zhang “FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising” In IEEE Transactions on Image Processing 27.9 Institute of ElectricalElectronics Engineers (IEEE, 2018, pp. 4608–4622 DOI: 10.1109/tip.2018.2839891.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.