STUDY AND ANALYSIS OF DEEP LEARNING FOR IMAGE RESTORATION
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2025
|
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901957130584064 |
|---|---|
| author | Y. Tresa |
| author_facet | Y. Tresa |
| contents | <p>Image restoration is an important area in computer vision and image processing that <br>aims to restore high quality images from degraded input images. Many of the past image <br>restoration algorithms relied on established techniques developed within filtering and <br>regularization. While these traditional restoration techniques have produced good results, and <br>have been widely utilized - they have been outperformed by deep learning methods. Several <br>different kinds of deep learning methods including convolutional neural networks (CNNs), <br>generative models, and residual learning strategies have been shown to outperform several <br>tasks[2] [3] [10]. related to image restoration, such as denoising, deblurring, inpainting, and super<br>resolution. In this paper we describe several important deep learning models and architectures <br>for image restoration, we take the opportunity to contrast and compare these methods with <br>classical methods, and we highlight some of the challenges and best direction for future work. </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17752518 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | STUDY AND ANALYSIS OF DEEP LEARNING FOR IMAGE RESTORATION Y. Tresa <p>Image restoration is an important area in computer vision and image processing that <br>aims to restore high quality images from degraded input images. Many of the past image <br>restoration algorithms relied on established techniques developed within filtering and <br>regularization. While these traditional restoration techniques have produced good results, and <br>have been widely utilized - they have been outperformed by deep learning methods. Several <br>different kinds of deep learning methods including convolutional neural networks (CNNs), <br>generative models, and residual learning strategies have been shown to outperform several <br>tasks[2] [3] [10]. related to image restoration, such as denoising, deblurring, inpainting, and super<br>resolution. In this paper we describe several important deep learning models and architectures <br>for image restoration, we take the opportunity to contrast and compare these methods with <br>classical methods, and we highlight some of the challenges and best direction for future work. </p> |
| title | STUDY AND ANALYSIS OF DEEP LEARNING FOR IMAGE RESTORATION |
| url | https://doi.org/10.5281/zenodo.17752518 |