Using Fractional Super-Resolution to Improve Lossy Compression of Point Cloud Geometry
Authors:
- Tomás M. BorgesTBTomás M. Borges
- University of BrasiliaUBUniversity of Brasilia
- Renan Utida Barbosa FerreiraRFRenan Utida Barbosa Ferreira
- Diogo C. GarciaDGDiogo C. Garcia
- Ricardo L. de QueirozRQRicardo L. de Queiroz
Open Access
- 1 January 2023
- journal article
- research article
- Published by Sociedad Brasileira de Telecomunicacoes in Journal of Communication and Information Systems
- Vol. 38 (1) , 169-173
Abstract
We present a method for post-processing point clouds’ geometric information by applying a previously proposed fractional super-resolution technique to clouds compressed and decoded with MPEG’s G-PCC codec. In some sense, this is a continuation of that previous work, which requires only a downscaled point cloud and a scaling factor, both of which are provided by the G-PCC codec. For non-solid point clouds, an a priori down-scaling is required for improved efficiency. The method is compared to the GPCC itself, as well as machine-learning-based techniques. Results show a great improvement in quality over GPCC and comparable performance to the latter techniques, with the advantage of not needing any kind of previous training.Keywords
This publication has 14 references indexed in Scilit:
- Fractional Super-Resolution of Voxelized Point CloudsIEEE Transactions on Image Processing, 2022
- Adaptive Deep Learning-Based Point Cloud Geometry CodingIEEE Journal of Selected Topics in Signal Processing, 2020
- Lossy Point Cloud Geometry Compression Via Dyadic Decomposition2020
- Super-Resolution of 3D Color Point Clouds Via Fast Graph Total Variation2020
- An overview of ongoing point cloud compression standardization activities: video-based (V-PCC) and geometry-based (G-PCC)APSIPA Transactions on Signal and Information Processing, 2020
- PU-GAN: A Point Cloud Upsampling Adversarial Network2019
- 3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals2019
- Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression2019
- Geometry Coding for Dynamic Voxelized Point Clouds Using Octrees and Multiple ContextsIEEE Transactions on Image Processing, 2019
- PU-Net: Point Cloud Upsampling Network2018