Buisine Jérôme, Bigand André, Synave Rémi, Delepoulle Samuel, Renaud Christophe
University of Littoral Côte d'Opale (ULCO), LISIC, BP 719, 62228 Calais CEDEX, France.
Entropy (Basel). 2021 Jan 6;23(1):75. doi: 10.3390/e23010075.
The estimation of image quality and noise perception still remains an important issue in various image processing applications. It has also become a hot topic in the field of photo-realistic computer graphics where noise is inherent in the calculation process. Unlike natural-scene images, however, a reference image is not available for computer-generated images. Thus, classic methods to assess noise quantity and stopping criterion during the rendering process are not usable. This is particularly important in the case of global illumination methods based on stochastic techniques: They provide photo-realistic images which are, however, corrupted by stochastic noise. This noise can be reduced by increasing the number of paths, as proved by Monte Carlo theory, but the problem of finding the right number of paths that are required in order to ensure that human observers cannot perceive any noise is still open. Until now, the features taking part in the human evaluation of image quality and the remaining perceived noise are not precisely known. Synthetic image generation tends to be very expensive and the produced datasets are high-dimensional datasets. In that case, finding a stopping criterion using a learning framework is a challenging task. In this paper, a new method for characterizing computational noise for computer generated images is presented. The noise is represented by the entropy of the singular value decomposition of each block composing an image. These Singular Value Decomposition (SVD)-entropy values are then used as input to a recurrent neural network architecture model in order to extract image noise and in predicting a visual convergence threshold of different parts of any image. Thus a new no-reference image quality assessment is proposed using the relation between SVD-Entropy and perceptual quality, based on a sequence of distorted images. Experiments show that the proposed method, compared with experimental psycho-visual scores, demonstrates a good consistency between these scores and stopping criterion measures that we obtain.
在各种图像处理应用中，图像质量评估和噪声感知仍然是一个重要问题。在逼真的计算机图形领域，它也成为了一个热门话题，因为噪声在计算过程中是固有的。然而，与自然场景图像不同，计算机生成的图像没有参考图像可用。因此，在渲染过程中评估噪声量和停止准则的经典方法不可用。这在基于随机技术的全局光照方法中尤为重要：它们提供逼真的图像，但会被随机噪声破坏。正如蒙特卡罗理论所证明的，通过增加路径数量可以减少这种噪声，但找到确保人类观察者无法感知任何噪声所需的正确路径数量的问题仍然没有解决。到目前为止，参与人类图像质量评估的特征以及剩余的感知噪声尚不清楚。合成图像生成往往非常昂贵，并且生成的数据集是高维数据集。在这种情况下，使用学习框架找到停止准则是一项具有挑战性的任务。本文提出了一种用于表征计算机生成图像计算噪声的新方法。噪声由构成图像的每个块的奇异值分解的熵表示。然后，这些奇异值分解（SVD）熵值被用作递归神经网络架构模型的输入，以提取图像噪声并预测任何图像不同部分的视觉收敛阈值。因此，基于一系列失真图像，利用SVD熵与感知质量之间的关系，提出了一种新的无参考图像质量评估方法。实验表明，与实验心理视觉评分相比，该方法在这些评分与我们获得的停止准则测量之间表现出良好的一致性。
