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 2A
DTSTART;TZID=America/Denver:20240801T140000
DTEND;TZID=America/Denver:20240801T153000
UID:siggraph_SIGGRAPH 2024_sess104@linklings.com
SUMMARY:Procedural Geometry
DESCRIPTION:Surface-filling Curve Flows via Implicit Medial Axes\n\nWe int
 roduce a fast, robust, and user-controllable algorithm to generate surface
 -filling curves. We compute these curves through the gradient flow of a si
 mple sparse energy. Our algorithm makes minimal assumptions on the input s
 urface, achieving improved robustness. Our framework provides tuneable p..
 .\n\n\nYuta Noma (University of Tokyo, University of Toronto); Silvia Sell
 án (University of Toronto); Nicholas Sharp (NVIDIA); Karan Singh (Universi
 ty of Toronto); and Alec Jacobson (University of Toronto, Adobe Research)\
 n---------------------\nProcedural Geometry - Interactive Discussion\n\nAf
 ter the summary presentations, attendees will participate in an interactiv
 e discussion. Distributed around the room will be a series of poster board
 s for authors to gather around with the audience. Authors are invited to b
 ring any material related to their paper that could instigate further conv
 er...\n\n---------------------\nTerrain Amplification Using Multi Scale Er
 osion\n\nWe present a multi-scale amplification method producing a high-re
 solution, hydrologically consistent terrain. The method relies on a fast a
 nd accurate approximation of different erosion processes, including therma
 l, stream power erosion and deposition performed at different scales to ob
 tain a range ...\n\n\nHugo Schott (CNRS - LIRIS; INSA, Lyon); Eric Galin (
 CNRS - LIRIS, Université Claude Bernard Lyon 1); Eric Guérin (CNRS - LIRIS
 ; INSA, Lyon); Axel Paris (Adobe Research); and Adrien Peytavie (CNRS - LI
 RIS, Université Claude Bernard Lyon 1)\n---------------------\nInteractive
  Invigoration: Volumetric Modeling of Trees With Strands\n\nWe introduce a
 n interactive tree modeling approach that mimics tree secondary growth wit
 h strand-based volumetric representation. Our model enables interactive ge
 neration of complex detailed tree models with minimal effort by integratin
 g strands with an interactive tree development model and a set o...\n\n\nB
 osheng Li (Purdue University), Nikolas Schwarz (Kiel University), Wojtek P
 alubicki (AMU), Soeren Pirk (Kiel University), and Bedrich Benes (Purdue U
 niversity)\n---------------------\nRecompose Grammars for Procedural Archi
 tecture\n\nRecomp overcomes fundamental limitations of split grammars by i
 ntroducing structural shape recomposition and geometry component tagging. 
 It allows for selectively reversing the subdivision process, enabling a fl
 exible decompose-refine-recompose workflow and precise geometric control, 
 leading to sign...\n\n\nNiklaus Houska, Cheryl Lau, and Matthias Specht (E
 sri R&D Center Zurich)\n---------------------\nDeadWood: Including disturb
 ance and decay in the depiction of digital nature\n\nWe present a framewor
 k that combines an ecosystem simulation, which explicitly incorporates dis
 turbance events and decay processes, with a model realization process, whi
 ch balances the uniqueness arising from life history with the need for ins
 tancing due to memory constraints.\n\n\nAdrien Peytavie (Université Lyon 1
 , CNRS, LIRIS); James Gain (University of Cape Town); Eric Guérin (INSA, L
 yon); Oscar Argudo (Universitat Politècnica de Catalunya); Eric Galin (Uni
 versité Lyon 1, CNRS, LIRIS); and Adrien Peytavie\n---------------------\n
 Latent L-systems: Transformer-based Tree Generator\n\nThe study introduces
  a Transformer-based deep learning framework for generating 3D tree models
  using L-systems. Trained on 155k geometries, this neural model replaces m
 anual rule creation, accurately learning and generating L-strings. It show
 s high fidelity in branching patterns and geometric featur...\n\n\nJae Joo
 ng Lee, Bosheng Li, and Bedrich Benes (Purdue University) and Jae Joong Le
 e\n\nInterest Area: Research & Education\n\nKeyword: Geometry, Modeling\n\
 nRegistration Category: Full Conference, Full Conference Supporter, Virtua
 l Access, Exhibitor Full Conference, Thursday\n\nSession Chair: Roi Porann
 e (University of Haifa)
END:VEVENT
END:VCALENDAR
