A comparative analysis of SRGAN models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915066372161536 |
|---|---|
| author | Nikroo, Fatemeh Rezapoor Deshmukh, Ajinkya Sharma, Anantha Tam, Adrian Kumar, Kaarthik Norris, Cleo Dangi, Aditya |
| author_facet | Nikroo, Fatemeh Rezapoor Deshmukh, Ajinkya Sharma, Anantha Tam, Adrian Kumar, Kaarthik Norris, Cleo Dangi, Aditya |
| contents | In this study, we evaluate the performance of multiple state-of-the-art SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images which undergo degradation using a pipeline. Our results show that some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine. We observe that EDSR-BASE model from huggingface outperforms the remaining candidate models in terms of both quantitative metrics and subjective visual quality assessments with least compute overhead. Specifically, EDSR generates images with higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values and are seen to return high quality OCR results with Tesseract OCR engine. These findings suggest that EDSR is a robust and effective approach for single-image super-resolution and may be particularly well-suited for applications where high-quality visual fidelity is critical and optimized compute. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_09456 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A comparative analysis of SRGAN models Nikroo, Fatemeh Rezapoor Deshmukh, Ajinkya Sharma, Anantha Tam, Adrian Kumar, Kaarthik Norris, Cleo Dangi, Aditya Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Image and Video Processing In this study, we evaluate the performance of multiple state-of-the-art SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images which undergo degradation using a pipeline. Our results show that some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine. We observe that EDSR-BASE model from huggingface outperforms the remaining candidate models in terms of both quantitative metrics and subjective visual quality assessments with least compute overhead. Specifically, EDSR generates images with higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values and are seen to return high quality OCR results with Tesseract OCR engine. These findings suggest that EDSR is a robust and effective approach for single-image super-resolution and may be particularly well-suited for applications where high-quality visual fidelity is critical and optimized compute. |
| title | A comparative analysis of SRGAN models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Image and Video Processing |
| url | https://arxiv.org/abs/2307.09456 |