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:20260805T205510Z
LOCATION:Room 408 A
DTSTART;TZID=America/Los_Angeles:20260721T104500
DTEND;TZID=America/Los_Angeles:20260721T121500
UID:siggraph_SIGGRAPH 2026_sess130@linklings.com
SUMMARY:Materials & Textures
DESCRIPTION:Controllable Texture Tiling via Diffusion Transformers with Tr
 ansformed Rotary Embeddings\n\nWe introduce a novel Diffusion Transformer 
 framework for high-fidelity, controllable texture tiling. By leveraging Co
 ordinate-Transformed Rotary Embeddings, our method enables precise manipul
 ation of texture frequency, scale, and orientation. It seamlessly integrat
 es reference patterns into images w...\n\n\nJunrong Huang and Zhiyuan Zhan
 g (City University of Hong Kong), Rui Tang (Manycore Tech Inc.), Hongbo Fu
  (Hong Kong University of Science and Technology), and Jing Liao (City Uni
 versity of Hong Kong)\n---------------------\nVideoNeuMat: Neural Material
  Extraction from Generative Video Models\n\nVideoNeuMat extracts reusable 
 neural materials from video diffusion models. It fine-tunes a large video 
 model as a virtual gonioreflectometer and uses a Large Reconstruction Mode
 l (LRM) to reconstruct compact neural materials in a single pass. The resu
 lting materials are realistic, diverse, and gene...\n\n\nBowen Xue (Univer
 sity of Manchester); Saeed Hadadan (NVIDIA); Zheng Zeng (University of Cal
 ifornia Santa Barbara, NVIDIA); Fabrice Rousselle (NVIDIA); Zahra Montazer
 i (University of Manchester); and Milos Hasan (NVIDIA)\n------------------
 ---\nPureSample: Neural Materials Learned by Sampling Microgeometry\n\nPur
 eSample is a neural BRDF representation that learns material appearance di
 rectly from forward random walks on microgeometry. It enables efficient BR
 DF evaluation, importance sampling, and pdf evaluation using a flow-based 
 sampler and a lightweight view-dependent albedo network, supporting comple
 x...\n\n\nZixuan Li, Zixiong Wang, and Jian Yang (Nankai University); Milo
 š Hašan (NVIDIA); and Beibei Wang (Nanjing University)\n------------------
 ---\nFast and Accurate Gaussian Process Modelling of Real-World Materials\
 n\nWe propose a BRDF modeling method that provides accurate and compact re
 presentations for isotropic and anisotropic BRDFs. We propose new theoreti
 cal developments enabling tractable Gaussian Process BRDF regression, lead
 ing to analytical BRDF representations. State-of-the-art methods can be ou
 tperfor...\n\n\nArnau Colom (Pompeu Fabra University  Interactive Technolo
 gies Group (GTI)); Christian Bouville (Institut de Recherche en Informatiq
 ue et Systèmes Aléatoires (IRISA)); Julien Pettre (Institut National de Re
 cherche en Informatique et en Automatique (INRIA)  Rennes University, CNRS
 , IRISA); Kadi Bouatouch (Institut de Recherche en Informatique et Système
 s Aléatoires (IRISA)); Ricardo Marques (Pompeu Fabra University  Interacti
 ve Technologies Group (GTI)); and Arnau Colom\n---------------------\nSucc
 essive Height Preintegration for a Height-Interdependent Path Formulation 
 of Multiple Bounces in Smith Microfacet BRDFs\n\nClassic microfacet models
  for rendering account only for single-bounce light, leading to energy los
 s. We present a novel multiple-bounce Smith microfacet BRDF with a height-
 interdependent formulation, successive height preintegration, and an impro
 ved BRDF evaluation method. Our model can conserve en...\n\n\nSiyuan Zhang
  (Chiba University), Takuya Funatomi (Kyoto University), Yuki Fujimura and
  Yasuhiro Mukaigawa (Nara Institute of Science and Technology), and Hiroyu
 ki Kubo (Chiba University)\n---------------------\nRobust In-Engine Textur
 e Optimization from Inconsistent Generative Targets\n\nWe present a practi
 cal method for optimizing textures directly inside production rendering en
 gines from inconsistent AI-generated images. By handling geometric mismatc
 h and unreliable details, our approach avoids blur and ghosting, enabling 
 robust texture refinement without requiring differentiable ...\n\n\nTaejoo
 n Kim, Seung-Uk Yoon, Seong-Jae Lim, Bon-Woo Hwang, Kinam Kim, and Seung W
 ook Lee (Electronics and Telecommunications Research Institute (ETRI))\n--
 -------------------\nMaterials & Textures - Interactive Discussion\n\nAfte
 r the summary presentations, attendees will participate in an interactive 
 discussion. Outside the room will be a series of poster boards for authors
  to gather around with the audience. Authors are invited to bring any mate
 rial related to their paper that could instigate further conversation such
 ...\n\n\nInterest Area: Research & Education\n\nKeyword: Artificial Intell
 igence/Machine Learning, Modeling, Real-Time, Rendering\n\nRegistration Ca
 tegory: Full Conference Supporter, Full Conference\n\nSession Chair: Jeppe
  Revall Frisvad (Technical University of Denmark)
END:VEVENT
END:VCALENDAR