Cost Savings from Automatic Quality Assessment of Generated Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908600567332864 |
|---|---|
| author | Giro-i-Nieto, Xavier Andreou, Nefeli Liang, Anqi Baradad, Manel Moreno-Noguer, Francesc Martinez, Aleix |
| author_facet | Giro-i-Nieto, Xavier Andreou, Nefeli Liang, Anqi Baradad, Manel Moreno-Noguer, Francesc Martinez, Aleix |
| contents | Deep generative models have shown impressive progress in recent years, making it possible to produce high quality images with a simple text prompt or a reference image. However, state of the art technology does not yet meet the quality standards offered by traditional photographic methods. For this reason, production pipelines that use generated images often include a manual stage of image quality assessment (IQA). This process is slow and expensive, especially because of the low yield of automatically generated images that pass the quality bar. The IQA workload can be reduced by introducing an automatic pre-filtering stage, that will increase the overall quality of the images sent to review and, therefore, reduce the average cost required to obtain a high quality image. We present a formula that estimates the cost savings depending on the precision and pass yield of a generic IQA engine. This formula is applied in a use case of background inpainting, showcasing a significant cost saving of 51.61% obtained with a simple AutoML solution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16179 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cost Savings from Automatic Quality Assessment of Generated Images Giro-i-Nieto, Xavier Andreou, Nefeli Liang, Anqi Baradad, Manel Moreno-Noguer, Francesc Martinez, Aleix Computer Vision and Pattern Recognition I.4.9 Deep generative models have shown impressive progress in recent years, making it possible to produce high quality images with a simple text prompt or a reference image. However, state of the art technology does not yet meet the quality standards offered by traditional photographic methods. For this reason, production pipelines that use generated images often include a manual stage of image quality assessment (IQA). This process is slow and expensive, especially because of the low yield of automatically generated images that pass the quality bar. The IQA workload can be reduced by introducing an automatic pre-filtering stage, that will increase the overall quality of the images sent to review and, therefore, reduce the average cost required to obtain a high quality image. We present a formula that estimates the cost savings depending on the precision and pass yield of a generic IQA engine. This formula is applied in a use case of background inpainting, showcasing a significant cost saving of 51.61% obtained with a simple AutoML solution. |
| title | Cost Savings from Automatic Quality Assessment of Generated Images |
| topic | Computer Vision and Pattern Recognition I.4.9 |
| url | https://arxiv.org/abs/2510.16179 |