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:20260817T171538Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T104500
DTEND;TZID=Asia/Tokyo:20241205T105900
UID:siggraphasia_SIGGRAPH Asia 2024_sess128_papers_966@linklings.com
SUMMARY:AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius
DESCRIPTION:Xinzhe Wang, Ran Yi, and Lizhuang Ma (Shanghai Jiao Tong Unive
 rsity)\n\n3D Gaussian Splatting (3DGS) is a recent explicit 3D representat
 ion that has achieved high-quality reconstruction and real-time rendering 
 of complex scenes. However, the rasterization pipeline still suffers from 
 unnecessary overhead resulting from avoidable serial Gaussian culling, and
  uneven load due to the distinct number of Gaussian to be rendered across 
 pixels, which hinders wider promotion and application of 3DGS. In order to
  accelerate Gaussian splatting, we propose AdR-Gaussian, which moves part 
 of serial culling in Render stage into the earlier Preprocess stage to ena
 ble parallel culling, employing adaptive radius to narrow the rendering pi
 xel range for each Gaussian, and introduces a load balancing method to min
 imize thread waiting time during the pixel-parallel rendering. Our contrib
 utions are threefold, achieving a rendering speed of 310% while maintainin
 g equivalent or even better quality than the state-of-the-art. Firstly, we
  propose to early cull Gaussian-Tile pairs of low splatting opacity based 
 on an adaptive radius in the Gaussian-parallel Preprocess stage, which red
 uces the number of affected tile through the Gaussian bounding circle, thu
 s reducing unnecessary overhead and achieving faster rendering speed. Seco
 ndly, we further propose early culling based on axis-aligned bounding box 
 for Gaussian splatting, which achieves a more significant reduction in ine
 ffective expenses by accurately calculating the Gaussian size in the 2D di
 rections. Thirdly, we propose a balancing algorithm for pixel thread load,
  which compresses the information of heavy-load pixels to reduce thread wa
 iting time, and enhance information of light-load pixels to hedge against 
 rendering quality loss. Experiments on three datasets demonstrate that our
  algorithm can significantly improve the Gaussian Splatting rendering spee
 d.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguag
 e Format: English Language\n\nSession Chair: Manolis Savva (Simon Fraser U
 niversity)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_966&sess=sess128
END:VEVENT
END:VCALENDAR