BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190059Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250813T104500
DTEND;TZID=America/Los_Angeles:20250813T123500
UID:siggraph_SIGGRAPH 2025_sess119@linklings.com
SUMMARY:Splatting Bigger, Faster, and Adaptive
DESCRIPTION:When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance 
 Field Rendering\n\nWe introduce Gaussian-enhanced Surfels (GESs), a bi-sca
 le representation combining opaque surfels and Gaussians for high-fidelity
  radiance field rendering. GES is entirely sorting free, enabling high-fid
 elity view-consistent rendering with ultra fast speeds.\n\n\nKeyang Ye, Ti
 anjia Shao, and Kun Zhou (Zhejiang University)\n---------------------\nDon
 ’t Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and
  Rendering Scattering and Emissive Media\n\nWe formalize the path-tracing 
 of volumes composed of anisotropic kernel mixture models. Our work enables
  computing physically-based light transport on complex volumetric assets e
 fficiently, on tiny memory budgets. We further introduce Epanechnikov kern
 els as an efficient alternative in kernel-based ...\n\n\nJorge Condor (Uni
 versita della Svizzera Italiana); Sébastien Speierer, Lukas Bode, Božič Al
 jaž, and Simon Green (Meta Reality Labs); Piotr Didyk (Universita della Sv
 izzera Italiana); Adrián Jarabo (Meta Reality Labs); and Jorge Condor\n---
 ------------------\nFLoD: Integrating Flexible Level of Detail into 3D Gau
 ssian Splatting for Customizable Rendering\n\nFlexible Level of Detail (FL
 oD) integrates the concept of LoD into 3DGS using a multi-level representa
 tion built with 3D Gaussian scale constraints and level-by-level training 
 strategy. FLoD enables flexible rendering through single-level or selectiv
 e rendering for optimal image quality under varyin...\n\n\nYunji Seo, Youn
 g Sun Choi, HyunSeung Son, and Youngjung Uh (Yonsei University)\n---------
 ------------\nDeformable Beta Splatting\n\nDeformable Beta Splatting (DBS)
  is a novel approach for real-time radiance field rendering that leverages
  deformable Beta Kernels with adaptive frequency control for both geometry
  and color encoding. DBS captures complex geometries and lighting with sta
 te-of-the-art fidelity, while only using 45% fe...\n\n\nRong Liu (USC Inst
 itute for Creative Technologies (ICT)), Dylan Sun (University of Southern 
 California), Meida Chen (USC Institute for Creative Technologies (ICT)), Y
 ue Wang (University of Southern California), and Andrew Feng (USC Institut
 e for Creative Technologies (ICT))\n---------------------\nVirtualized 3D 
 Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Ren
 dering of Composed Scenes\n\nV3DG achieves real-time rendering of massive 
 3D Gaussians in large, composed scenes through a novel LOD approach.\nInsp
 ired by Nanite, V3DG processes detailed 3D assets into clusters at various
  granularities offline, and selectively renders 3D Gaussians at runtime—fl
 exibly balancing rendering s...\n\n\nXijie Yang (Zhejiang University, Shan
 ghai Artificial Intelligence Laboratory); Linning Xu (The Chinese Universi
 ty of Hong Kong); Lihan Jiang (University of Science and Technology of Chi
 na, Shanghai Artificial Intelligence Laboratory); Dahua Lin (The Chinese U
 niversity of Hong Kong, Shanghai Artificial Intelligence Laboratory); and 
 Bo Dai (University of Hong Kong)\n---------------------\nImage-GS: Content
 -Adaptive Image Representation via 2D Gaussians\n\nWe introduce Image-GS, 
 a content-adaptive image representation based on colored 2D Gaussians. Ima
 ge-GS achieves remarkable rate-distortion performance across diverse image
 s and textures while supporting hardware-friendly fast random access and f
 lexible quality control through a smooth level-of-detai...\n\n\nYunxiang Z
 hang and Bingxuan Li (New York University), Alexandr Kuznetsov (Advanced M
 icro Devices (AMD)), Akshay Jindal and Stavros Diolatzis (Intel Corporatio
 n), Kenneth Chen (New York University), Anton Sochenov and Anton Kaplanyan
  (Intel Corporation), and Qi Sun (New York University)\n------------------
 ---\nSplatting Bigger, Faster, and Adaptive - Interactive Discussion\n\nAf
 ter the summary presentations, attendees will participate in an interactiv
 e discussion. Outside the room will be a series of poster boards for autho
 rs to gather around with the audience. Authors are invited to bring any ma
 terial related to their paper that could instigate further conversation su
 ch...\n\n---------------------\n3DGS2: Near Second-order Converging 3D Gau
 ssian Splatting\n\nThis paper introduces a nearly second-order convergent 
 training algorithm for 3D Gaussian Splatting that exploits independent ker
 nel attributes and sparse coupling across images. By constructing and solv
 ing small Newton systems for parameter groups, it achieves about an-order 
 faster training while m...\n\n\nLei Lan (University of Utah; State Key Lab
  of CAD and CG, Zhejiang University); Tianjia Shao (Zhejiang University); 
 Zixuan Lu and Yu Zhang (University of Utah); Chenfanfu Jiang (UCLA); and Y
 in Yang (University of Utah)\n\nInterest Area: Research & Education\n\nRec
 ording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistra
 tion Category: Full Conference, Virtual Access, Wednesday\n\nSession Chair
 : Gurprit Singh (Advanced Micro Devices, Inc. (AMD))
END:VEVENT
END:VCALENDAR