This website requires JavaScript.

DDH-QA: A Dynamic Digital Humans Quality Assessment Database

Zicheng ZhangYingjie ZhouWei Sun ...+3 Guangtao Zhai
Dec 2022
摘要
In recent years, large amounts of effort have been put into pushing forwardthe real-world application of dynamic digital human (DDH). However, mostcurrent quality assessment research focuses on evaluating static 3D models andusually ignores motion distortions. Therefore, in this paper, we construct alarge-scale dynamic digital human quality assessment (DDH-QA) database withdiverse motion content as well as multiple distortions to comprehensively studythe perceptual quality of DDHs. Both model-based distortion (noise,compression) and motion-based distortion (binding error, motion unnaturalness)are taken into consideration. Ten types of common motion are employed to drivethe DDHs and a total of 800 DDHs are generated in the end. Afterward, we renderthe video sequences of the distorted DDHs as the evaluation media and carry outa well-controlled subjective experiment. Then a benchmark experiment isconducted with the state-of-the-art video quality assessment (VQA) methods andthe experimental results show that existing VQA methods are limited inassessing the perceptual loss of DDHs. The database will be made publiclyavailable to facilitate future research.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答