Recent advances in capture technologies have increased the production of 3D content in the form of Point Clouds (PCs). The perceived quality of such data can be impacted by typical processing including acquisition, compression, transmission, visualization, etc. In this paper, we propose a learning-based method that efficiently predicts the quality of distorted PCs through a set of features extracted from the reference PC and its degraded version. The quality index is obtained here by combining the considered features using a Support Vector Regression (SVR) model. The performance contribution of each considered feature and their combination are compared. We then discuss the experimental results obtained in the context of state-of-the-art methods using 2 publicly available datasets. We also evaluate the ability of our method to predict unknown PCs through a cross-dataset evaluation. The results show the relevance of introducing a learning step to merge features for the quality assessment of such data.
In recent years, PCs have become very popular for a wide range of applications, such as immersive virtual reality scenarios. As a consequence, in the last couple of years, there has been a great effort to develop novel acquisition, representation, compression, and transmission solutions for PC contents in the research community. In particular, the development of objective quality assessment methods that are able to predict the perceptual quality of PCs. In this paper, we present an effective novel method for assessing the quality of PCs, which is based on descriptors that extract perceptual color distance-based texture information of PC contents, called Perceptual Color Distance Patterns (PCDP). In this framework, the statistics of the extracted information are used to model the PC visual quality. Experimental results show that the proposed framework exhibit good and robust performance when compared with several state-of-the-art point cloud quality assessment (PCQA) methods.
Point clouds are essential for storage and transmission of 3D content. As they can entail significant volumes of data, point cloud compression is crucial for practical usage. Recently, point cloud geometry compression approaches based on deep neural networks have been explored. In this paper, we evaluate the ability to predict perceptual quality of typical voxel-based loss functions employed to train these networks. We find that the commonly used focal loss and weighted binary cross entropy are poorly correlated with human perception. We thus propose a perceptual loss function for 3D point clouds which outperforms existing loss functions on the ICIP2020 subjective dataset. In addition, we propose a novel truncated distance field voxel grid representation and find that it leads to sparser latent spaces and loss functions that are more correlated with perceived visual quality compared to a binary representation. The source code is available at <uri>https://github.com/mauriceqch/2021_pc_perceptual_loss</uri>.
We improve High Dynamic Range (HDR) Image Quality Assessment (IQA) using a full reference approach that combines results from various quality metrics (HDR-CQM). We combine metrics designed for different applications such as HDR, SDR and color difference measures in a single unifying framework using simple linear regression techniques and other non-linear machine learning (ML) based approaches. We find that using a non-linear combination of scores from different quality metrics using support vector machine is better at prediction than the other techniques such as random forest, random trees, multilayer perceptron or a radial basis function network. To improve performance and reduce complexity of the proposed approach, we use the Sequential Floating Selection technique to select a subset of metrics from a list of quality metrics. We evaluate the performance on two publicly available calibrated databases with different types of distortion and demonstrate improved performance using HDR-CQM as compared to several existing IQA metrics. We also show the generality and robustness of our approach using cross-database evaluation.