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:20260417T190116Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250813T154500
DTEND;TZID=America/Los_Angeles:20250813T171500
UID:siggraph_SIGGRAPH 2025_sess125@linklings.com
SUMMARY:Gaussian Reconstruction
DESCRIPTION:Photoreal Scene Reconstruction from an Egocentric Device\n\nTh
 is paper investigates photorealistic scene reconstruction using videos cap
 tured from an egocentric device in high dynamic range. It presents a novel
  system utilizing visual-inertial bundle adjustment and a physical image f
 ormation model that handles camera motion artifacts. The experiments using
  P...\n\n\nZhaoyang Lv, Maurizio Monge, Ka Chen, Yufeng Zhu, Michael Goese
 le, Jakob Engel, Zhao Dong, and Richard Newcombe (Reality Labs Research, M
 eta)\n---------------------\nGaussian Reconstruction - Interactive Discuss
 ion\n\nAfter the summary presentations, attendees will participate in an i
 nteractive discussion. Outside the room will be a series of poster boards 
 for authors to gather around with the audience. Authors are invited to bri
 ng any material related to their paper that could instigate further conver
 sation such...\n\n---------------------\nMonocular Online Reconstruction w
 ith Enhanced Detail Preservation\n\nWe propose a high-quality online recon
 struction pipeline for monocular input streams, reconstructing environment
 s with detail across multiple levels while maintaining high speed.\n\n\nSo
 ngyin Wu (Meta Reality Labs Research, University of California Santa Barba
 ra); Zhaoyang Lv, Yufeng Zhu, Duncan Frost, and Zhengqin Li (Meta Reality 
 Labs Research); Ling-Qi Yan (University of California Santa Barbara); and 
 Carl Ren, Richard Newcombe, and Zhao Dong (Meta Reality Labs Research)\n--
 -------------------\nSplat4D: Diffusion-Enhanced 4D Gaussian Splatting for
  Temporally and Spatially Consistent Content Creation\n\nSplat4D generates
  high-fidelity 4D content from monocular videos by integrating multi-view 
 rendering, inconsistency identification, a video diffusion model, and asym
 metric U-Net refinement. Our framework maintains spatial-temporal consiste
 ncy while preserving details and following user guidance, ach...\n\n\nMing
 hao Yin (University of Hong Kong); Yukang Cao (Nanyang Technological Unive
 rsity, Singapore); Songyou Peng (Google DeepMind); and Kai Han (University
  of Hong Kong)\n---------------------\nOn-the-fly Reconstruction for Large
 -Scale Novel View Synthesis from Unposed Images\n\nWe propose a fast, on-t
 he-fly 3D Gaussian Splatting method that jointly estimates poses and recon
 structs scenes. Through fast pose initialization, direct primitive samplin
 g, and scalable clustering and merging, it efficiently handles diverse ord
 ered image sequences of arbitrary length.\n\n\nAndreas Meuleman, Ishaan Sh
 ah, and Alexandre Lanvin (INRIA, Université Côte d'Azur); Bernhard Kerbl (
 TU Wien); and George Drettakis (INRIA, Université Côte d'Azur)\n----------
 -----------\n4D Gaussian Videos with Motion Layering\n\nWe present 4D Gaus
 sian Video (4DGV) for high-quality, low-storage volumetric video reconstru
 ction and real-time streaming. Our method effectively handles complex moti
 on and enables effective motion compression, achieving superior performanc
 e in both reconstruction quality and storage efficiency.\n\n\nPinxuan Dai,
  Peiquan Zhang, and Zheng Dong (Zhejiang University); Ke Xu (City Universi
 ty of Hong Kong); Yifan Peng (The University of Hong Kong); Dandan Ding (H
 angzhou Normal University); Yujun Shen (Ant Group); Yin Yang (The Universi
 ty of Utah); Xinguo Liu (Zhejiang University); Rynson W.H. Lau (City Unive
 rsity of Hong Kong); and Weiwei Xu (State Key Lab CAD&CG, Zhejiang Univers
 ity)\n---------------------\nTransparentGS: Fast Inverse Rendering of Tran
 sparent Objects with Gaussians\n\nWe propose TransparentGS, a fast inverse
  rendering pipeline for transparent objects based on 3D-GS. The main contr
 ibutions are three-fold: efficient transparent Gaussian primitives for spe
 cular refraction, GaussProbe to encode ambient light and nearby contents, 
 and the IterQuery algorithm to reduce ...\n\n\nLetian Huang, Dongwei Ye, J
 ialin Dan, and Chengzhi Tao (State Key Lab for Novel Software Technology, 
 Nanjing University); Huiwen Liu (TMCC, College of Computer Science, Nankai
  University); Kun Zhou (State Key Lab of CAD&CG, Zhejiang University; Inst
 itute of Hangzhou Holographic Intelligent Technology); Bo Ren (TMCC, Colle
 ge of Computer Science, Nankai University); and Yuanqi Li, Yanwen Guo, and
  Jie Guo (State Key Lab for Novel Software Technology, Nanjing University)
 \n\nInterest Area: Research & Education\n\nRecording: Livestreamed, Not Li
 vestreamed, Recorded, Not Recorded\n\nRegistration Category: Full Conferen
 ce, Virtual Access, Wednesday\n\nSession Chair: Paul Debevec (Netflix, USC
  Institute for Creative Technologies (ICT))
END:VEVENT
END:VCALENDAR