Texture synthesis quality assessment using perceptual texture similarity
Texture synthesis quality assessment using perceptual texture similarity
复制标题
DOI：
10.1016/j.knosys.2020.105591
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Xinghui Dong;Huiyu Zhou
中科院分区：
文献类型：
--
作者：
Xinghui Dong;Huiyu Zhou
纹理合成在电脑游戏和电影行业中扮演着重要的角色。虽然已经有了广泛的研究，但对合成纹理的质量评估却很少受到关注。受感知纹理相似度估计研究进展的启发，我们提出了一种纹理综合质量评估（TSQA）方法。据我们所知，这是首次尝试在TSQA任务中利用感知纹理相似性。我们特别介绍了两种用于综合质量评价的感知相似原则。相应地，我们训练了两个随机森林（RF）回归器。给定一对样本和合成纹理，这两个回归量可以分别用于预测合成纹理的全局和局部质量分数。从这两个分数中生成一个总分。我们的研究结果表明，由预训练的卷积神经网络（CNN）提取的深度词袋（BoW）描述符比其他九种类型的手工制作或CNN描述符和图像质量评估度量以及提出的TSQA方法表现更好，或与之相当。
Texture synthesis plays an important role in computer game and movie industries. Although it has been widely studied, the assessment of the quality of the synthesised textures has received little attention. Inspired by the research progress in perceptual texture similarity estimation, we propose a Texture Synthesis Quality Assessment (TSQA) approach. To our knowledge, this is the first attempt to exploit perceptual texture similarity for the TSQA task. In particular, we introduce two perceptual similarity principles for synthesis quality assessment. Correspondingly, we train two Random Forest (RF) regressors. Given a pair of sample and synthesised textures, the two regressors can be used to predict theglobalandlocalquality scores of the synthesised texture respectively. Anoverallscore is generated from the two scores. Our results show that the deep Bag-of-Words (BoW) descriptors, extracted by a pre-trained Convolutional Neural Network (CNN), perform better than, or comparably to, the other nine types of hand-crafted or CNN descriptors and an image quality assessment measure, together with the proposed TSQA approach.