Image Inpainting of Portraits Artwork Design and Implementation
In modern society, the restoration of artwork has become increasingly important. Generative models can provide reference images for the damaged or blurred core areas of these artworks. This paper simulates artificial damage to classic portrait paintings in the Art Portraits dataset by adding center...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03026.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206606140276736 |
|---|---|
| author | Zhang Hongting |
| author_facet | Zhang Hongting |
| author_sort | Zhang Hongting |
| collection | DOAJ |
| description | In modern society, the restoration of artwork has become increasingly important. Generative models can provide reference images for the damaged or blurred core areas of these artworks. This paper simulates artificial damage to classic portrait paintings in the Art Portraits dataset by adding center masks during data preprocessing and then implements the image inpainting task. During the training phase, the Denoising Diffusion Probabilistic Model (DDPM) is fine-tuned by progressively adding noise to the center-masked images in the noising stage, followed by denoising in the denoising stage to generate images. The generated images are compared with the original undamaged images through loss calculations to optimize the model. Additionally, a Generative Adversarial Network (GAN), which has shown promising results on other datasets, is used as a baseline for comparison. The damaged images are used as inputs, and the generated images are compared to the ground truth to evaluate the performance of both models. In the testing phase, two widely used metrics in image evaluation, Mean Squared Error (MSE) and Fréchet Inception Distance (FID), are introduced to assess the performance. The fine-tuned DDPM achieves an MSE of 0.2622 and an FID of 16.85, while the GAN scores 0.2835 and 22.78, respectively. Since lower values indicate higher fidelity in reproducing the original image, which is crucial for art restoration, the conclusion drawn from this paper is that the fine-tuned DDPM demonstrates higher accuracy and is more suitable for restoration projects related to Art Portraits. |
| format | Article |
| id | doaj-art-fb536f0c4f084550943cee234fae511b |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-fb536f0c4f084550943cee234fae511b2025-02-07T08:21:11ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700302610.1051/itmconf/20257003026itmconf_dai2024_03026Image Inpainting of Portraits Artwork Design and ImplementationZhang Hongting0Computer Science, Zhejiang University of TechnologyIn modern society, the restoration of artwork has become increasingly important. Generative models can provide reference images for the damaged or blurred core areas of these artworks. This paper simulates artificial damage to classic portrait paintings in the Art Portraits dataset by adding center masks during data preprocessing and then implements the image inpainting task. During the training phase, the Denoising Diffusion Probabilistic Model (DDPM) is fine-tuned by progressively adding noise to the center-masked images in the noising stage, followed by denoising in the denoising stage to generate images. The generated images are compared with the original undamaged images through loss calculations to optimize the model. Additionally, a Generative Adversarial Network (GAN), which has shown promising results on other datasets, is used as a baseline for comparison. The damaged images are used as inputs, and the generated images are compared to the ground truth to evaluate the performance of both models. In the testing phase, two widely used metrics in image evaluation, Mean Squared Error (MSE) and Fréchet Inception Distance (FID), are introduced to assess the performance. The fine-tuned DDPM achieves an MSE of 0.2622 and an FID of 16.85, while the GAN scores 0.2835 and 22.78, respectively. Since lower values indicate higher fidelity in reproducing the original image, which is crucial for art restoration, the conclusion drawn from this paper is that the fine-tuned DDPM demonstrates higher accuracy and is more suitable for restoration projects related to Art Portraits.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03026.pdf |
| spellingShingle | Zhang Hongting Image Inpainting of Portraits Artwork Design and Implementation ITM Web of Conferences |
| title | Image Inpainting of Portraits Artwork Design and Implementation |
| title_full | Image Inpainting of Portraits Artwork Design and Implementation |
| title_fullStr | Image Inpainting of Portraits Artwork Design and Implementation |
| title_full_unstemmed | Image Inpainting of Portraits Artwork Design and Implementation |
| title_short | Image Inpainting of Portraits Artwork Design and Implementation |
| title_sort | image inpainting of portraits artwork design and implementation |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03026.pdf |
| work_keys_str_mv | AT zhanghongting imageinpaintingofportraitsartworkdesignandimplementation |