Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Static Point Clouds Compression efficiency of MPEG point clouds coding standardsPublication . Prazeres, João Pedro Casanova; Pinheiro, António Manuel GonçalvesRecent advances in the consumption of 3D content creates the necessity of efficient ways to visualize and transmit 3D content. As a result, methods to obtain that same content have been evolving, leading to the development of new methods of representations, namely point clouds and light fields. A point cloud represents a set of points with associated Cartesian coordinates associated with each point(x, y, z), as well as being able to contain even more information inside that point (color, material, texture, etc). This kind of representation changes the way on how 3D content in consumed, having a wide range of applications, from videogaming to medical ones. However, since this type of data carries so much information within itself, they are data-heavy, making the storage and transmission of content a daunting task. To resolve this issue, MPEG created a point cloud coding normalization project, giving birth to V-PCC (Video-based Point Cloud Coding) and G-PCC (Geometry-based Point Cloud Coding) for static content. Firstly, a general analysis of point clouds is made, spanning from their possible solutions, to their acquisition. Secondly, point cloud codecs are studied, namely VPCC and G-PCC from MPEG. Then, a state of art study of quality evaluation is performed, namely subjective and objective evaluation. Finally, a report on the JPEG Pleno Point Cloud, in which an active colaboration took place, is made, with the comparative results of the two codecs and used metrics.
- Point cloud quality evaluation: Towards a definition for test conditionsPublication . Cruz, Luís; Dumic, Emil; Alexiou, Evangelos; Prazeres, João; Duarte, Rafael; Pereira, Manuela; Pinheiro, Antonio M. G.; Ebrahimi, TouradjRecently stakeholders in the area of multimedia representation and transmission have been looking at plenoptic technologies to improve immersive experience. Among these technologies, point clouds denote a volumetric information representation format with important applications in the entertainment, automotive and geographical mapping industries. There is some consensus that state-of-the-art solutions for efficient storage and communication of point clouds are far from satisfactory. This paper describes a study on point cloud quality evaluation, conducted in the context of JPEG Pleno to help define the test conditions of future compression proposals. A heterogeneous set of static point clouds in terms of number of points, geometric structure and represented scenarios were selected and compressed using octree-pruning and a projection-based method, with three different levels of degradation. The models were comprised of both geometrical and color information and were displayed using point sizes large enough to ensure observation of watertight surfaces. The stimuli under assessment were presented to the observers on 2D displays as animations, after defining suitable camera paths to enable visualization of the models in their entirety and realistic consumption. The experiments were carried out in three different laboratories and the subjective scores were used in a series of correlation studies to benchmark objective quality metrics and assess inter-laboratory consistency.
- Quality Evaluation of Machine Learning-based Point Cloud Coding SolutionsPublication . Prazeres, João; Rodrigues, Rafael; Pereira, Manuela; Pinheiro, Antonio M. G.In this paper, a quality evaluation of three point cloud coding solutions based on machine learning technology is presented, notably, ADLPCC, PCC_GEO_CNN, and PCGC, as well as LUT_SR, which uses multi-resolution Look-Up Tables. Moreover, the MPEG G-PCC was used as an anchor. A set of six point clouds, representing both landscapes and objects were coded using the five encoders at different bit rates, and a subjective test, where the distorted and reference point clouds were rotated in a video sequence side by side, is carried out to assess their performance. Furthermore, the performance of point cloud objective quality metrics that usually provide a good representation of the coded content is analyzed against the subjective evaluation results. The obtained results suggest that some of these metrics fail to provide a good representation of the perceived quality, and thus are not suitable to evaluate some distortions created by machine learning-based solutions. A comparison between the analyzed metrics and the type of represented scene or codec is also presented.
- On the stability of point cloud machine learning based codingPublication . Prazeres, João; Rodrigues, Rafael; Pereira, Manuela; Pinheiro, Antonio M. G.This paper analyses the performance of two of the most well known deep learning-based point cloud coding solutions, considering the training conditions. Several works have recently been published on point cloud machine learning-based coding, following the recent tendency on image coding. These codecs are typically seen as a set of predefined trained machines. However, the performance of such models is usually very dependent of their training, and little work has been considered on the stability of the codecs’ performance, as well as the possible influence of the loss function parameters, and the increasing number of training epochs. The evaluation experiments are supported in a generic test set with point clouds representing objects and also more complex scenes, using the point to point metric (PSNR D1), as several studies revealed the good quality representation of this geometry-only point cloud metric.