Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: You, Kang, Liu, Kai, Yu, Li, Gao, Pan, Ding, Dandan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929323429068800
author You, Kang
Liu, Kai
Yu, Li
Gao, Pan
Ding, Dandan
author_facet You, Kang
Liu, Kai
Yu, Li
Gao, Pan
Ding, Dandan
contents Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a crucial requirement in real-world application. In this paper, we propose Pointsoup, an efficient learning-based geometry codec that attains high-performance and extremely low-decoding-latency simultaneously. Inspired by conventional Trisoup codec, a point model-based strategy is devised to characterize local surfaces. Specifically, skin features are embedded from local windows via an attention-based encoder, and dilated windows are introduced as cross-scale priors to infer the distribution of quantized features in parallel. During decoding, features undergo fast refinement, followed by a folding-based point generator that reconstructs point coordinates with fairly fast speed. Experiments show that Pointsoup achieves state-of-the-art performance on multiple benchmarks with significantly lower decoding complexity, i.e., up to 90$\sim$160$\times$ faster than the G-PCCv23 Trisoup decoder on a comparatively low-end platform (e.g., one RTX 2080Ti). Furthermore, it offers variable-rate control with a single neural model (2.9MB), which is attractive for industrial practitioners.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13550
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
You, Kang
Liu, Kai
Yu, Li
Gao, Pan
Ding, Dandan
Computer Vision and Pattern Recognition
Image and Video Processing
Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a crucial requirement in real-world application. In this paper, we propose Pointsoup, an efficient learning-based geometry codec that attains high-performance and extremely low-decoding-latency simultaneously. Inspired by conventional Trisoup codec, a point model-based strategy is devised to characterize local surfaces. Specifically, skin features are embedded from local windows via an attention-based encoder, and dilated windows are introduced as cross-scale priors to infer the distribution of quantized features in parallel. During decoding, features undergo fast refinement, followed by a folding-based point generator that reconstructs point coordinates with fairly fast speed. Experiments show that Pointsoup achieves state-of-the-art performance on multiple benchmarks with significantly lower decoding complexity, i.e., up to 90$\sim$160$\times$ faster than the G-PCCv23 Trisoup decoder on a comparatively low-end platform (e.g., one RTX 2080Ti). Furthermore, it offers variable-rate control with a single neural model (2.9MB), which is attractive for industrial practitioners.
title Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2404.13550