BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_327@linklings.com
SUMMARY:3QNet: 3D Point Cloud Geometry Quantization Compression Network
DESCRIPTION:Technical Papers\n\n3QNet: 3D Point Cloud Geometry Quantizatio
 n Compression Network\n\nHuang, zhang, Chen, Ding, Tai...\n\nSince the dev
 elopment of 3D applications, the point cloud, as a spatial description eas
 ily acquired by sensors, has been widely used in multiple areas such as SL
 AM and 3D reconstruction. Point Cloud Compression (PCC) has also attracted
  more attention as a primary step before point cloud transferring and savi
 ng, where the geometry compression is an important component of PCC to com
 press the points geometrical structures. However, existing non-learning-ba
 sed geometry compression methods are often limited by manually pre-defined
  compression rules. Though learning-based compression methods can signific
 antly improve the algorithm performances by learning compression rules fro
 m data, they still have some defects. Voxel-based compression networks int
 roduce precision errors due to the voxelized operations, while point-based
  methods may have relatively weak robustness and are mainly designed for s
 parse point clouds. In this work, we propose a novel learning-based point 
 cloud compression framework named 3D Point Cloud Geometry Quantiation Comp
 ression Network (3QNet), which overcomes the robustness limitation of exis
 ting point-based methods and can handle dense points. By learning a codebo
 ok including common structural features from simple and sparse shapes, 3QN
 et can efficiently deal with multiple kinds of point clouds. According to 
 experiments on object models, indoor scenes, and outdoor scans, 3QNet can 
 achieve better compression performances than many representative methods.\
 n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE 
 ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_327&sess=sess15
 3
END:VEVENT
END:VCALENDAR