BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171536Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T105600
DTEND;TZID=Asia/Tokyo:20241206T110800
UID:siggraphasia_SIGGRAPH Asia 2024_sess142_papers_408@linklings.com
SUMMARY:Large Scale Farm Scene Modeling from Remote Sensing Imagery
DESCRIPTION:Zhiqi Xiao and Hao Jiang (Institute of Computing Technology, C
 hinese Academy of Sciences; University of Chinese Academy of Sciences); Zh
 igang Deng (University of Houston); and Ran Li, Wenwei Han, and Zhaoqi Wan
 g (Institute of Computing Technology, Chinese Academy of Sciences; Univers
 ity of Chinese Academy of Sciences)\n\nIn this paper we propose a scalable
  framework for large-scale farm scene modeling that utilizes remote sensin
 g data, specifically satellite images. Our approach begins by accurately e
 xtracting and categorizing the distributions of various scene elements fro
 m satellite images into four distinct layers: fields, trees, roads, and gr
 asslands. For each layer, we introduce a set of controllable Parametric La
 yout Models (PLMs). These models are capable of learning layout parameters
  from satellite images, enabling them to generate complex, large-scale far
 m scenes that closely reproduce reality across multiple scales. Additional
 ly, our framework provides intuitive control for users to adjust layout pa
 rameters to simulate different stages of crop growth and planting patterns
 . This adaptability makes our model an excellent tool for graphics and vir
 tual reality applications. Experimental results demonstrate that our appro
 ach can rapidly generate a variety of realistic and highly detailed farm s
 cenes with minimal inputs.\n\nRegistration Category: Full Access, Full Acc
 ess Supporter\n\nLanguage Format: English Language\n\nSession Chair: Maria
  Larsson (The University of Tokyo)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_408&sess=sess142
END:VEVENT
END:VCALENDAR