Point clouds have become increasingly prevalent in representing 3D scenes within virtual environments, alongside 3D meshes. Their ease of capture has facilitated a wide array of applications on mobile devices, from smartphones to autonomous vehicles. Notably, point cloud compression has reached an advanced stage and has been standardized. However, the availability of quality assessment datasets, which are essential for developing improved objective quality metrics, remains limited. In this paper, we introduce BASICS, a large-scale quality assessment dataset tailored for static point clouds. The BASICS dataset comprises 75 unique point clouds, each compressed with four different algorithms including a learning-based method, resulting in the evaluation of nearly 1500 point clouds by 3500 unique participants. Furthermore, we conduct a comprehensive analysis of the gathered data, benchmark existing point cloud quality assessment metrics and identify their limitations. By publicly releasing the BASICS dataset, we lay the foundation for addressing these limitations and fostering the development of more precise quality metrics.

Three-dimensional models have been extensively used in several applications including computer-aided design (CAD), video games, medical imaging due to the processing capability improvement of computers, and the development of network bandwidth. Therefore, the necessity of implementing 3D mesh watermarking schemes aiming to protect copyright has increased considerably. In this paper, a blind robust 3D mesh watermarking method based on mesh saliency and wavelet transform for copyright protection is proposed. The watermark is inserted by quantifying the wavelet coefficients using quantization index modulation (QIM) according to the mesh saliency of the 3D semiregular mesh. The synchronizing primitive is the distance between the mesh center and salient points in the descending order. The experimental results show the high imperceptibility of the proposed scheme while ensuring a good robustness against a wide range of attacks including smoothing, additive noise, element reordering, similarity transformations, etc.

Human visual Attention modelling is a persistent interdisciplinary research challenge, gaining new interest in recent years mainly due to the latest developments in deep learning. That is particularly evident in saliency benchmarks. Novel deep learning-based visual saliency models show promising results in capturing high-level (top-down) human visual attention processes. Therefore, they strongly differ from the earlier approaches, mainly characterised by low-level (bottom-up) visual features. These developments account for innate human selectivity mechanisms that are reliant on both high- and low-level factors. Moreover, the two factors interact with each other. Motivated by the importance of these interactions, in this project, we tackle visual saliency modelling holistically, examining if we could consider both high- and low-level features that govern human attention. Specifically, we propose a novel method SAtSal (Self-Attention Saliency). SAtSal leverages both high and low-level features using a multilevel merging of skip connections during the decoding stage. Consequently, we incorporate convolutional self-attention modules on skip connection from the encoder to the decoder network to properly integrate the valuable signals from multilevel spatial features. Thus, the self-attention modules learn to filter out the latent representation of the salient regions from the other irrelevant information in an embedded and joint manner with the main encoder-decoder model backbone. Finally, we evaluate SAtSal against various existing solutions to validate our approach, using the well-known standard saliency benchmark MIT300. To further examine SAtSal’s robustness on other image types, we also evaluate it on the Le-Meur saliency painting benchmark.

A number of full reference and reduced reference methods have been proposed in order to estimate the perceived visual quality of 3D meshes. However, in most practical situations, there is a limited access to the information related to the reference and the distortion type. For these reasons, the development of a no-reference mesh visual quality (MVQ) approach is a critical issue, and more emphasis needs to be devoted to blind methods. In this work, we propose a no-reference convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes. The method is called SCNN-BMQA (3D visual saliency and CNN for blind mesh quality assessment). The main contribution is the usage of a CNN and 3D visual saliency to estimate the perceived visual quality of distorted meshes. To do so, the CNN architecture is fed by small patches selected carefully according to their level of saliency. First, the visual saliency of the 3D mesh is computed. Afterward, we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Then the obtained views are split into 2D small patches that pass through a saliency filter in order to select the most relevant patches. Finally, a CNN is used for the feature learning and the quality score estimation. Extensive experiments are conducted on four prominent MVQ assessment databases, including several tests to study the effect of the CNN parameters, the effect of visual saliency and comparison with existing methods. Results show that the trained CNN achieves good rates in terms of correlation with human judgment and outperforms the most effective state-of-the-art methods.

Digital representation of 3D content in the form of 3D point clouds (PC) has gained increasing interest and has emerged in various computer vision applications. However, various degradation may appear on the PC during acquisition, transmission, or treatment steps in the 3D processing pipeline. Therefore, several Full-Reference, Reduced-Reference, and No-Reference metrics have been proposed to estimate the visual quality of PC. However, Full-Reference and Reduced-Reference metrics require reference information, which is not accessible in real-world applications, and No-Reference metrics still lack precision in evaluating the PC quality. In this context, we propose a novel deep learning-based method for No-Reference Point Cloud Quality Assessment (NR-PCQA) that aims to automatically predict the perceived visual quality of the PC without using the reference content. More specifically, in order to imitate the human visual system during the PC quality evaluation that captures the geometric and color degradation, we render the PC into different 2D views using a perspective projection. Then, the projected 2D views are divided into patches that are fed to a Convolutional Neural Network (CNN) to learn sophisticated and discriminative visual quality features for evaluating the local quality of each patch. Finally, the overall quality score of the PC is obtained by pooling the quality score patches. We conduct extensive experiments on three benchmark databases: ICIP2020, SJTU, and WPC, and we compare the proposed model to the existing Full-Reference, Reduced-Reference, and No-Reference state-of-the-art methods. Based on the experimental results, our proposed model achieves high correlations with the subjective quality scores and outperforms the state-of-the-art methods.

This paper proposes a new method for blind mesh visual quality assessment (MVQA) based on a graph convolutional network. For that, we address the node classification problem to predict the perceived visual quality. First, two matrices represent the 3D mesh: a graph adjacency matrix and a feature matrix. Both matrices are used as input to a shallow graph convolutional network. The network consists of two convolutional layers followed by a max-pooling layer to provide the final feature representation. With this structure, the Softmax classifier predicts the quality score category without the reference mesh’s availability. Experiments are conducted on four publicly available databases constructed explicitly for the mesh quality assessment task. We investigate several perceptual and visual features to select the most effective combination. Comparisons with the state-of-the-art alternative methods show the effectiveness of the proposed framework.