Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Yueyu, Gong, Ran, Wang, Yao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914956549554176
author Hu, Yueyu
Gong, Ran
Wang, Yao
author_facet Hu, Yueyu
Gong, Ran
Wang, Yao
contents Point cloud is a promising 3D representation for volumetric streaming in emerging AR/VR applications. Despite recent advances in point cloud compression, decoding and rendering high-quality images from lossy compressed point clouds is still challenging in terms of quality and complexity, making it a major roadblock to achieve real-time 6-Degree-of-Freedom video streaming. In this paper, we address this problem by developing a point cloud compression scheme that generates a bit stream that can be directly decoded to renderable 3D Gaussians. The encoder and decoder are jointly optimized to consider both bit-rates and rendering quality. It significantly improves the rendering quality while substantially reducing decoding and rendering time, compared to existing point cloud compression methods. Furthermore, the proposed scheme generates a scalable bit stream, allowing multiple levels of details at different bit-rate ranges. Our method supports real-time color decoding and rendering of high quality point clouds, thus paving the way for interactive 3D streaming applications with free view points.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
Hu, Yueyu
Gong, Ran
Wang, Yao
Computer Vision and Pattern Recognition
Image and Video Processing
Point cloud is a promising 3D representation for volumetric streaming in emerging AR/VR applications. Despite recent advances in point cloud compression, decoding and rendering high-quality images from lossy compressed point clouds is still challenging in terms of quality and complexity, making it a major roadblock to achieve real-time 6-Degree-of-Freedom video streaming. In this paper, we address this problem by developing a point cloud compression scheme that generates a bit stream that can be directly decoded to renderable 3D Gaussians. The encoder and decoder are jointly optimized to consider both bit-rates and rendering quality. It significantly improves the rendering quality while substantially reducing decoding and rendering time, compared to existing point cloud compression methods. Furthermore, the proposed scheme generates a scalable bit stream, allowing multiple levels of details at different bit-rate ranges. Our method supports real-time color decoding and rendering of high quality point clouds, thus paving the way for interactive 3D streaming applications with free view points.
title Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2406.05915