Advancing Video Quality Assessment for AIGC

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yue, Xinli, Sun, Jianhui, Kong, Han, Yao, Liangchao, Wang, Tianyi, Li, Lei, Rao, Fengyun, Lv, Jing, Xia, Fan, Deng, Yuetang, Wang, Qian, Zhao, Lingchen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909322910367744
author Yue, Xinli
Sun, Jianhui
Kong, Han
Yao, Liangchao
Wang, Tianyi
Li, Lei
Rao, Fengyun
Lv, Jing
Xia, Fan
Deng, Yuetang
Wang, Qian
Zhao, Lingchen
author_facet Yue, Xinli
Sun, Jianhui
Kong, Han
Yao, Liangchao
Wang, Tianyi
Li, Lei
Rao, Fengyun
Lv, Jing
Xia, Fan
Deng, Yuetang
Wang, Qian
Zhao, Lingchen
contents In recent years, AI generative models have made remarkable progress across various domains, including text generation, image generation, and video generation. However, assessing the quality of text-to-video generation is still in its infancy, and existing evaluation frameworks fall short when compared to those for natural videos. Current video quality assessment (VQA) methods primarily focus on evaluating the overall quality of natural videos and fail to adequately account for the substantial quality discrepancies between frames in generated videos. To address this issue, we propose a novel loss function that combines mean absolute error with cross-entropy loss to mitigate inter-frame quality inconsistencies. Additionally, we introduce the innovative S2CNet technique to retain critical content, while leveraging adversarial training to enhance the model's generalization capabilities. Experimental results demonstrate that our method outperforms existing VQA techniques on the AIGC Video dataset, surpassing the previous state-of-the-art by 3.1% in terms of PLCC.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14888
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advancing Video Quality Assessment for AIGC
Yue, Xinli
Sun, Jianhui
Kong, Han
Yao, Liangchao
Wang, Tianyi
Li, Lei
Rao, Fengyun
Lv, Jing
Xia, Fan
Deng, Yuetang
Wang, Qian
Zhao, Lingchen
Computer Vision and Pattern Recognition
In recent years, AI generative models have made remarkable progress across various domains, including text generation, image generation, and video generation. However, assessing the quality of text-to-video generation is still in its infancy, and existing evaluation frameworks fall short when compared to those for natural videos. Current video quality assessment (VQA) methods primarily focus on evaluating the overall quality of natural videos and fail to adequately account for the substantial quality discrepancies between frames in generated videos. To address this issue, we propose a novel loss function that combines mean absolute error with cross-entropy loss to mitigate inter-frame quality inconsistencies. Additionally, we introduce the innovative S2CNet technique to retain critical content, while leveraging adversarial training to enhance the model's generalization capabilities. Experimental results demonstrate that our method outperforms existing VQA techniques on the AIGC Video dataset, surpassing the previous state-of-the-art by 3.1% in terms of PLCC.
title Advancing Video Quality Assessment for AIGC
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.14888