Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator

arXiv:2404.07698v1 Announce Type: new
Abstract: The widespread usage of point clouds (PC) for immersive visual applications has resulted in the use of very heterogeneous receiving conditions and devices, notably in terms of network, hardware, and display capabilities. In this scenario, quality scalability, i.e., the ability to reconstruct a signal at different qualities by progressively decoding a single bitstream, is a major requirement that has yet to be conveniently addressed, notably in most learning-based PC coding solutions. This paper proposes a …

abstract applications arxiv capabilities cloud coding cs.ai cs.cv cs.lg devices estimator geometry hardware immersive network probability quality scalability scalable signal terms type usage visual