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:20260417T190106Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250814T140000
DTEND;TZID=America/Los_Angeles:20250814T153000
UID:siggraph_SIGGRAPH 2025_sess123@linklings.com
SUMMARY:Neural Materials & LOD
DESCRIPTION:Appearance-Preserving Scene Aggregation for Level-of-Detail Re
 ndering\n\nWe present a novel volumetric representation for the aggregated
  appearance of complex scenes and a pipeline for level-of-detail generatio
 n and rendering. Our representation preserves accurate far-field appearanc
 e and spatial correlation from scene geometry. Our method faithfully repro
 duces appearanc...\n\n\nYang Zhou and Tao Huang (University of California 
 Santa Barbara), Ravi Ramamoorthi (University of California San Diego), Pra
 deep Sen and Ling-Qi Yan (University of California Santa Barbara), and Lin
 g-Qi Yan\n---------------------\nNeural Materials & LOD - Interactive Disc
 ussion\n\nAfter the summary presentations, attendees will participate in a
 n interactive discussion. Outside the room will be a series of poster boar
 ds for authors to gather around with the audience. Authors are invited to 
 bring any material related to their paper that could instigate further con
 versation such...\n\n---------------------\nRNA: Relightable Neural Assets
 \n\nWe propose a neural representation for 3D assets with complex shading.
  We precompute shading and scattering on ground-truth geometry, enabling h
 igh-fidelity rendering with full relightability, eliminating complex shadi
 ng models and multiple scattering paths, offering significant speed-ups an
 d seamle...\n\n\nKrishna Mullia, Fujun Luan, Xin Sun, and Miloš Hašan (Ado
 be Research) and Krishna Mullia\n---------------------\nGenerative Neural 
 Materials\n\nWe present the first generative model for neural BTFs, enabli
 ng single-shot generation from arbitrary text or image prompts. To achieve
  this, we introduce a universal neural material basis and train a conditio
 nal diffusion model to generate materials in this basis from flash images,
  natural images a...\n\n\nNithin Raghavan (University of California San Di
 ego), Krishna Mullia (Adobe Research), Alexander Trevithick (University of
  California San Diego), Fujun Luan and Miloš Hašan (Adobe Research), and R
 avi Ramamoorthi (University of California San Diego)\n--------------------
 -\nGenerative detail enhancement for physically based materials\n\nWe pres
 ent a tool for enhancing the detail of physically based materials using an
  off-the-shelf diffusion model and inverse rendering. Our goal is to enhan
 ce the visual fidelity of materials with detail that is often tedious to a
 uthor, by adding signs of wear, aging, weathering, etc.\n\n\nSaeed Hadadan
  (University of Maryland College Park, NVIDIA); Benedikt Bitterli, Tizian 
 Zeltner, Jan Novák, Fabrice Rousselle, Jacob Munkberg, Jon Hasselgren, and
  Bartlomiej Wronski (NVIDIA); and Matthias Zwicker (University of Maryland
  College Park)\n---------------------\nTowards Comprehensive Neural Materi
 als: Dynamic Structure-Preserving Synthesis with Accurate Silhouette at In
 stant Inference Speed\n\nWe challenge the comprehensive neural material re
 presentation by thoroughly considering the essential aspects of the comple
 te appearance. We introduce an int8-quantized model that keeps high fideli
 ty while achieving an order of magnitude speedup compared to previous meth
 ods, and a controllable struc...\n\n\nZilin Xu (University of California S
 anta Barbara); Xiang Chen (Shandong University); Chen Liu (Zhejiang Lingdi
  Digital Technology Co.,Ltd); Beibei Wang (Nanjing University); Lu Wang (S
 handong University); Zahra Montazeri (University of Manchester); and Ling-
 Qi Yan (University of California Santa Barbara)\n---------------------\nNe
 ural BRDF Importance Sampling by Reparameterization\n\nWe introduce a repa
 rameterization-based formulation of neural BRDF importance sampling. Compa
 ring to previous methods that construct a probability transform to the BRD
 F through multi-step invertible neural networks, our BRDF sampling is in s
 ingle step without needing network invertibility, achieving...\n\n\nLiwen 
 Wu (University of California San Diego); Sai Bi (Adobe Research); Zexiang 
 Xu (Hillbot); Hao Tan, Kai Zhang, and Fujun Luan (Adobe Research); Haolin 
 Lu (Max Planck Institute for Informatics); and Ravi Ramamoorthi (Universit
 y of California San Diego)\n\nInterest Area: Research & Education\n\nRecor
 ding: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistrati
 on Category: Full Conference, Virtual Access, Thursday\n\nSession Chair: T
 homas Leimkühler (MPI Informatik)
END:VEVENT
END:VCALENDAR