Q-Refine: A Perceptual Quality Refiner for AI-Generated Image
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917557733163008 |
|---|---|
| author | Li, Chunyi Wu, Haoning Zhang, Zicheng Hao, Hongkun Zhang, Kaiwei Bai, Lei Liu, Xiaohong Min, Xiongkuo Lin, Weisi Zhai, Guangtao |
| author_facet | Li, Chunyi Wu, Haoning Zhang, Zicheng Hao, Hongkun Zhang, Kaiwei Bai, Lei Liu, Xiaohong Min, Xiongkuo Lin, Weisi Zhai, Guangtao |
| contents | With the rapid evolution of the Text-to-Image (T2I) model in recent years, their unsatisfactory generation result has become a challenge. However, uniformly refining AI-Generated Images (AIGIs) of different qualities not only limited optimization capabilities for low-quality AIGIs but also brought negative optimization to high-quality AIGIs. To address this issue, a quality-award refiner named Q-Refine is proposed. Based on the preference of the Human Visual System (HVS), Q-Refine uses the Image Quality Assessment (IQA) metric to guide the refining process for the first time, and modify images of different qualities through three adaptive pipelines. Experimental shows that for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs of different qualities. It can be a general refiner to optimize AIGIs from both fidelity and aesthetic quality levels, thus expanding the application of the T2I generation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01117 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Q-Refine: A Perceptual Quality Refiner for AI-Generated Image Li, Chunyi Wu, Haoning Zhang, Zicheng Hao, Hongkun Zhang, Kaiwei Bai, Lei Liu, Xiaohong Min, Xiongkuo Lin, Weisi Zhai, Guangtao Computer Vision and Pattern Recognition Image and Video Processing With the rapid evolution of the Text-to-Image (T2I) model in recent years, their unsatisfactory generation result has become a challenge. However, uniformly refining AI-Generated Images (AIGIs) of different qualities not only limited optimization capabilities for low-quality AIGIs but also brought negative optimization to high-quality AIGIs. To address this issue, a quality-award refiner named Q-Refine is proposed. Based on the preference of the Human Visual System (HVS), Q-Refine uses the Image Quality Assessment (IQA) metric to guide the refining process for the first time, and modify images of different qualities through three adaptive pipelines. Experimental shows that for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs of different qualities. It can be a general refiner to optimize AIGIs from both fidelity and aesthetic quality levels, thus expanding the application of the T2I generation models. |
| title | Q-Refine: A Perceptual Quality Refiner for AI-Generated Image |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2401.01117 |