BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T172800
DTEND;TZID=Asia/Tokyo:20241203T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess111_papers_539@linklings.com
SUMMARY:V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynami
 c Gaussians
DESCRIPTION:Technical Papers\n\nPenghao Wang, Zhirui Zhang, Liao Wang, Kai
 xin Yao, and Siyuan Xie (ShanghaiTech University, NeuDim Inc.); Jingyi Yu 
 (ShanghaiTech University); Minye Wu (KU Leuven); and Lan Xu (ShanghaiTech 
 University)\n\nExperiencing high-fidelity volumetric video as seamlessly a
 s 2D videos is a long-held dream. However, current dynamic 3DGS methods, d
 espite their high rendering quality, face challenges in streaming on mobil
 e devices due to computational and bandwidth constraints. In this paper, w
 e introduce V3 (Viewing Volumetric Videos), a novel approach that enables 
 high-quality mobile rendering through the streaming of dynamic Gaussians. 
 Our key innovation is to view dynamic 3DGS as 2D videos, facilitating the 
 use of hardware video codecs. Additionally, we propose a two-stage trainin
 g strategy to reduce storage requirements with rapid training speed. The f
 irst stage employs hash encoding and shallow MLP to learn motion, then red
 uces the number of Gaussians through pruning to meet the streaming require
 ments, while the second stage fine-tunes other Gaussian attributes using r
 esidual entropy loss and temporal loss to improve temporal continuity. Thi
 s strategy, which disentangles motion and appearance, maintains high rende
 ring quality with compact storage requirements. Meanwhile, we designed a m
 ulti-platform player to decode and render 2D Gaussian videos. Extensive ex
 periments demonstrate the effectiveness of V3, outperforming other methods
  by enabling high-quality rendering and streaming on common devices, which
  is unseen before. As the first to stream dynamic Gaussians on mobile devi
 ces, our companion player offers users an unprecedented volumetric video e
 xperience, including smooth scrolling and instant sharing.\n\nRegistration
  Category: Full Access, Full Access Supporter\n\nLanguage Format: English 
 Language\n\nSession Chair: Yifan Peng (University of Hong Kong)
URL:https://asia.siggraph.org/2024/program/?id=papers_539&sess=sess111
END:VEVENT
END:VCALENDAR