BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240801T140000
DTEND;TZID=America/Denver:20240801T153000
UID:siggraph_SIGGRAPH 2024_sess144@linklings.com
SUMMARY:Radiance Field Processing
DESCRIPTION:TensoSDF: Roughness-aware Tensorial Representation for Robust 
 Geometry and Material Reconstruction\n\nWe propose a novel framework for r
 obust geometry and material reconstruction. The framework's core is the ro
 ughness-aware incorporation of the radiance and reflectance fields to reco
 nstruct arbitrary reflective objects. The proposed TensoSDF representation
  enhances the geometry details while acceler...\n\n\nJia Li (Shandong Univ
 ersity), Beibei Wang (Nanjing University), Lu Wang (Shandong University), 
 and Lei Zhang (The Hong Kong Polytechnic University)\n--------------------
 -\nBilateral Guided Radiance Field Processing\n\nGiven a set of multi-view
  images with photometric variation, our method reconstructs a high-quality
  radiance field without "floaters" by disentangling the inconsistent camer
 a processing across different views. Furthermore, we propose a radiance-fi
 nishing approach that can lift user-provided 2D retou...\n\n\nYuehao Wang,
  Chaoyi Wang, Bingchen Gong, and Tianfan Xue (The Chinese University of Ho
 ng Kong)\n---------------------\nN-Dimensional Gaussians for Fitting of Hi
 gh Dimensional Functions\n\nWe propose the use of N-Dimensional Gaussian m
 ixtures to fit high dimensional functions, applicable to various applicati
 ons such as neural global illumination and novel view synthesis for comple
 x anisotropic effects. Our method offers quality similar to implicit metho
 ds with orders of magnitude fast...\n\n\nStavros Diolatzis, Tobias Zirr, a
 nd Alexander Kuznetsov (Intel Labs); Georgios Kopanas (INRIA, Université C
 ôte d'Azur); and Anton Kaplanyan (Intel Labs)\n---------------------\nA Co
 nstruct-optimize Approach to Sparse View Synthesis Without Camera Pose\n\n
 We leverage the 3D Gaussian splatting method to develop a novel construct-
 and-optimize method for sparse view synthesis without camera poses. We dem
 onstrate results on the Tanks and Temples and Static Hikes datasets with a
 s few as three widely spaced views, showing significantly better quality t
 han ...\n\n\nKaiwen Jiang, Yang Fu, Mukund Varma T, Yash Belhe, Xiaolong W
 ang, Hao Su, and Ravi Ramamoorthi (University of California San Diego)\n--
 -------------------\nRip-NeRF: Anti-aliasing Radiance Fields With Ripmap-e
 ncoded Platonic Solids\n\nRip-NeRF is an anti-aliasing 3D scene representa
 tion that integrates anisotropic pre-filtering with Platonic solid faces. 
 It captures high-frequency anisotropic details with swift training times, 
 achieving 37.23 PSNR on the Blender dataset within 2.6 hours of training. 
 Due to its simplicity, other t...\n\n\nJunchen Liu (Beihang University); W
 enbo Hu (Tencent AI Lab); Zhuo Yang and Jianteng Chen (Beijing Institute o
 f Technology); Guoliang Wang and Xiaoxue Chen (Tsinghua University); Yanto
 ng Cai (Dermatology Hospital, Southern Medical University); and Huan-ang G
 ao and Hao Zhao (Tsinghua University)\n---------------------\nBinary Opaci
 ty Grids: Capturing Fine Geometric Detail for Mesh-based View Synthesis\n\
 nWe reconstruct meshes from multi-view images that contain fine geometric 
 detail yet are suitable for high-quality view synthesis on low-powered dev
 ices. To this end, we model the scene as a high-resolution binary opacity 
 grid and shoot multiple rays per pixel to be able to reason about subpixel
  stru...\n\n\nChristian Reiser (Tübingen AI Center, University of Tübingen
 ; Google Research); Stephan Garbin, Pratul Srinivasan, Dor Verbin, Richard
  Szeliski, Ben Mildenhall, Jonathan Barron, and Peter Hedman (Google Resea
 rch); and Andreas Geiger (Tübingen AI Center, University of Tübingen)\n---
 ------------------\nRadiance Field Processing - Interactive Discussion\n\n
 After the summary presentations, attendees will participate in an interact
 ive discussion. Distributed around the room will be a series of poster boa
 rds for authors to gather around with the audience. Authors are invited to
  bring any material related to their paper that could instigate further co
 nver...\n\n\nInterest Area: Research & Education\n\nRegistration Category:
  Full Conference, Full Conference Supporter, Virtual Access, Exhibitor Ful
 l Conference, Thursday\n\nSession Chair: Nathan Carr (Adobe)
END:VEVENT
END:VCALENDAR