Development of perceptual image quality database and assessment for AI generated facial images
In recent years, advancement in generative Text-to-image (T2I) models have made great strides, contributing to the emergence of AI-Generated Facial Images (AGFIs), with diverse applications in various fields including entertainment, education and research. However, different AGFIs possess large qual...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175321 |
| _version_ | 1824454764144885760 |
|---|---|
| author | Tan, Xin Kai |
| author2 | Lin Weisi |
| author_facet | Lin Weisi Tan, Xin Kai |
| author_sort | Tan, Xin Kai |
| collection | NTU |
| description | In recent years, advancement in generative Text-to-image (T2I) models have made great strides, contributing to the emergence of AI-Generated Facial Images (AGFIs), with diverse applications in various fields including entertainment, education and research. However, different AGFIs possess large quality variance, demanding the need for image quality benchmark models that are consistent with human subjective ratings. Therefore, this project examines various popular T2I AI-Generated Image (AGI) models and leveraged different prompts to generate AGFIs. Through rigorous subjective assessments, a new human perception-based quality database for T2I AGFIs, titled AGFI-500, is established. Subsequently, a benchmark experiment is conducted on this database. Using different popular Image Quality Assessment (IQA) metrics from existing literature to evaluate the performance of current IQA methodology in the domain of scoring perceptual quality of AGFIs. Lastly, a novel solution for No-Reference Image Quality Assessment (NR-IQA) termed Generated Facial NR-IQA (GFNR-IQA), is proposed as an alternative to existing techniques for assessing individual AGFIs and generating perceived quality score. |
| first_indexed | 2025-02-19T03:27:29Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/175321 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:27:29Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1753212024-04-26T15:44:28Z Development of perceptual image quality database and assessment for AI generated facial images Tan, Xin Kai Lin Weisi School of Computer Science and Engineering WSLin@ntu.edu.sg Computer and Information Science AI Image quality assessment In recent years, advancement in generative Text-to-image (T2I) models have made great strides, contributing to the emergence of AI-Generated Facial Images (AGFIs), with diverse applications in various fields including entertainment, education and research. However, different AGFIs possess large quality variance, demanding the need for image quality benchmark models that are consistent with human subjective ratings. Therefore, this project examines various popular T2I AI-Generated Image (AGI) models and leveraged different prompts to generate AGFIs. Through rigorous subjective assessments, a new human perception-based quality database for T2I AGFIs, titled AGFI-500, is established. Subsequently, a benchmark experiment is conducted on this database. Using different popular Image Quality Assessment (IQA) metrics from existing literature to evaluate the performance of current IQA methodology in the domain of scoring perceptual quality of AGFIs. Lastly, a novel solution for No-Reference Image Quality Assessment (NR-IQA) termed Generated Facial NR-IQA (GFNR-IQA), is proposed as an alternative to existing techniques for assessing individual AGFIs and generating perceived quality score. Bachelor's degree 2024-04-23T06:09:58Z 2024-04-23T06:09:58Z 2024 Final Year Project (FYP) Tan, X. K. (2024). Development of perceptual image quality database and assessment for AI generated facial images. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175321 https://hdl.handle.net/10356/175321 en SCSE23-0612 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science AI Image quality assessment Tan, Xin Kai Development of perceptual image quality database and assessment for AI generated facial images |
| title | Development of perceptual image quality database and assessment for AI generated facial images |
| title_full | Development of perceptual image quality database and assessment for AI generated facial images |
| title_fullStr | Development of perceptual image quality database and assessment for AI generated facial images |
| title_full_unstemmed | Development of perceptual image quality database and assessment for AI generated facial images |
| title_short | Development of perceptual image quality database and assessment for AI generated facial images |
| title_sort | development of perceptual image quality database and assessment for ai generated facial images |
| topic | Computer and Information Science AI Image quality assessment |
| url | https://hdl.handle.net/10356/175321 |
| work_keys_str_mv | AT tanxinkai developmentofperceptualimagequalitydatabaseandassessmentforaigeneratedfacialimages |