电子学报2025，Vol.53Issue(1)：193-208,16.DOI:10.12263/DZXB.20240101
融合多层特征的窗口6DoF合成视频质量评价
Quality Assessment for Windowed-6DoF Synthesized Video Based on Multilayer Features Fusion
摘要
Abstract
Six degrees of freedom(6DoF)video,allowing users to experience the scene from omnidirectional and ar-bitrary perspective,is the development direction of the next-generation immersive video system.The windowed 6DoF video with limited degrees of freedom is a hot research topic in recent years.This paper proposes a subjective database and an ob-jective quality assessment method for the windowed 6DoF synthesized video.For subjective database,we build a subjective quality database called Windowed-6DoF.The database contains 128 windowed 6DoF synthesized videos which involve dis-comfort caused by two viewpoint switching paths,distortions caused by four rendering schemes,and four levels of compres-sion.Then subjective quality tests are conducted on the database and the test results are analyzed.For objective quality as-sessment,we design a no reference quality assessment method for windowed 6DoF synthesized video which fuses multilay-er features.Tchebichef moment is used to extract the low layer shape features of temporal video slices.Resnet-50 network is used to extract the high-level semantic features of video in temporal and spatial domains,and consequently reduce the di-mensionality of features.Finally,the random forest is used to fuse the low layer shape features and high layer semantic fea-tures,and train the quality assessment model of windowed 6DoF synthesized video.We respectively test the method on the proposed Windowed-6DoF database and IRCCyN/IVC DIBR database.The experimental results show that the Pearson lin-ear correlation coefficient of the proposed method are 0.932 7 and 0.858 1,respectively.The predicted scores of the objec-tive method are consistent with the subjective assessment scores.关键词
视频质量评价/窗口六自由度视频/交互路径/语义特征Key words
video quality assessment/windowed six degrees of freedom video/interaction path/semantic features分类
信息技术与安全科学引用本文复制引用
唐婷琰,邹文辉,彭宗举,陈芬,金充充..融合多层特征的窗口6DoF合成视频质量评价[J].电子学报,2025,53(1):193-208,16.基金项目
国家自然科学基金(No.62371081) （No.62371081）
重庆市自然科学基金(No.cstc2021jcyj-msxmX0411,No.CSTB2022NSCQ-MSX0873) National Natural Science Foundation of China(No.62371081) （No.cstc2021jcyj-msxmX0411,No.CSTB2022NSCQ-MSX0873）
National Natural Science Foun-dation of Chongqing(No.cstc2021jcyj-msxmX0411,No.CSTB2022NSCQ-MSX0873) （No.cstc2021jcyj-msxmX0411,No.CSTB2022NSCQ-MSX0873）
