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:20260817T171540Z
LOCATION:G510\, G Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T112000
DTEND;TZID=Asia/Tokyo:20241205T120000
UID:siggraphasia_SIGGRAPH Asia 2024_sess287@linklings.com
SUMMARY:Image-Based Reconstruction
DESCRIPTION:The Technical Communications program at SIGGRAPH Asia serves a
 s an invaluable platform for presenting cutting-edge work that may not nea
 tly align with the Technical Papers session. Attendees can expect to explo
 re fresh and thought-provoking ideas, glean practical insights from real-w
 orld production work, and discover innovative applications spanning variou
 s disciplines, from graphics and vision to AI and VR.\n\nDuring these sess
 ions, leading experts from academia and industry will present their latest
  findings, offering a glimpse into cutting-edge research and development. 
 From geometry and animation to virtual reality and machine learning, atten
 dees can expect to explore a diverse array of topics at the intersection o
 f graphics and other fields.\n\nUnder the overarching theme of Curious Min
 ds, attendees can delve into discussions surrounding innovation, interdisc
 iplinary discovery, and the role of education in shaping the future of tec
 hnology. Whether you’re a seasoned researcher or a curious enthusiast, the
  Technical Communications program promises to offer insights that spark cu
 riosity and inspire new perspectives.\n\nODA-GS: Occlusion- and Distortion
 -aware Gaussian Splatting for Indoor Scene Reconstruction\n\nWe propose OD
 A-GS, enhancing 3D Gaussian Splatting for indoor scene reconstruction by m
 itigating over-reconstruction and gradient dilution through occlusion-awar
 e gradient accumulation and post-pruning, resulting in improved visual qua
 lity.\n\n\nChai-Rong Lee, Ting-Yu Yen, Kai-Wen Hsiao, Shih-Hsuan Hung, She
 ng-Chi Hsu, and Min-Chun Hu (National Tsing Hua University); Chih-Yuan Yao
  (National Taiwan University of Science and Technology); and Hung-Kuo Chu 
 (National Tsing Hua University)\n---------------------\nSplanting: 3D plan
 t capture with gaussian splatting\n\nWe evaluate 3D gaussian splatting for
  capturing the structure and appearance of plants with self-occlusion. We 
 report and analyze exemplar splants across a range of plant species and gr
 owth stages.\n\n\nTommy Ojo, Thai La, Andrew Morton, and Ian Stavness (Uni
 versity of Saskatchewan)\n---------------------\nAn Evaluation Metric for 
 Single Image-to-3D Models Based on Object Detection Perspective\n\nWe prop
 ose a novel evaluation metric for "single image-to-3D" models based on obj
 ect detection perspective. This metric considers semantic information and 
 focuses especially on objects, using only one input image.\n\n\nYuiko Uchi
 da, Ren Togo, Keisuke Maeda, Takahiro Ogawa, and Miki Haseyama (Hokkaido U
 niversity)\n---------------------\nA Multi-flash Stereo Camera for Photo-r
 ealistic Capture of Small Scenes\n\nWe present a robot-mounted multi-flash
  stereo camera system to capture geometric and photometric data from small
  scenes to enable the creation of photorealistic, and relightable 3D asset
 s with few views.\n\n\nArkadeep Narayan Chaudhury (Carnegie Mellon Univers
 ity, Epic Games); Igor Vasiljevic, Sergey Zakharov, Vitor Guizilini, and R
 ares Ambrus (Toyota Research Institute); and Srinivasa Narasimhan and Chri
 stopher G. Atkeson (Carnegie Mellon Uniersity, Robotics Institute)\n\nRegi
 stration Category: Full Access, Full Access Supporter\n\nLanguage Format: 
 English Language\n\nSession Chair: Kaizhang Kang (Pohang University of Sci
 ence and Technology)
END:VEVENT
END:VCALENDAR
