Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.04715 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908405537439744 |
|---|---|
| author | Qi, Zelu Shi, Ping Zhang, Chaoyang Wang, Shuqi Zhao, Fei Pan, Da Ying, Zefeng |
| author_facet | Qi, Zelu Shi, Ping Zhang, Chaoyang Wang, Shuqi Zhao, Fei Pan, Da Ying, Zefeng |
| contents | The development of AI-Generated Video (AIGV) technology has been remarkable in recent years, significantly transforming the paradigm of video content production. However, AIGVs still suffer from noticeable visual quality defects, such as noise, blurriness, frame jitter and low dynamic degree, which severely impact the user's viewing experience. Therefore, an effective automatic visual quality assessment is of great importance for AIGV content regulation and generative model improvement. In this work, we decompose the visual quality of AIGVs into three dimensions: technical quality, motion quality, and video semantics. For each dimension, we design corresponding encoder to achieve effective feature representation. Moreover, considering the outstanding performance of large language models (LLMs) in various vision and language tasks, we introduce a LLM as the quality regression module. To better enable the LLM to establish reasoning associations between multi-dimensional features and visual quality, we propose a specially designed multi-modal prompt engineering framework. Additionally, we incorporate LoRA fine-tuning technology during the training phase, allowing the LLM to better adapt to specific tasks. Our proposed method achieved \textbf{second place} in the NTIRE 2025 Quality Assessment of AI-Generated Content Challenge: Track 2 AI Generated video, demonstrating its effectiveness. Codes can be obtained at https://github.com/QiZelu/AIGVEval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04715 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model Qi, Zelu Shi, Ping Zhang, Chaoyang Wang, Shuqi Zhao, Fei Pan, Da Ying, Zefeng Computer Vision and Pattern Recognition The development of AI-Generated Video (AIGV) technology has been remarkable in recent years, significantly transforming the paradigm of video content production. However, AIGVs still suffer from noticeable visual quality defects, such as noise, blurriness, frame jitter and low dynamic degree, which severely impact the user's viewing experience. Therefore, an effective automatic visual quality assessment is of great importance for AIGV content regulation and generative model improvement. In this work, we decompose the visual quality of AIGVs into three dimensions: technical quality, motion quality, and video semantics. For each dimension, we design corresponding encoder to achieve effective feature representation. Moreover, considering the outstanding performance of large language models (LLMs) in various vision and language tasks, we introduce a LLM as the quality regression module. To better enable the LLM to establish reasoning associations between multi-dimensional features and visual quality, we propose a specially designed multi-modal prompt engineering framework. Additionally, we incorporate LoRA fine-tuning technology during the training phase, allowing the LLM to better adapt to specific tasks. Our proposed method achieved \textbf{second place} in the NTIRE 2025 Quality Assessment of AI-Generated Content Challenge: Track 2 AI Generated video, demonstrating its effectiveness. Codes can be obtained at https://github.com/QiZelu/AIGVEval. |
| title | Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.04715 |