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:20250522T212947Z
LOCATION:Mile High Pre-Function Area
DTSTART;TZID=America/Denver:20240731T090000
DTEND;TZID=America/Denver:20240731T173000
UID:siggraph_SIGGRAPH 2024_sess417@linklings.com
SUMMARY:Posters: Rendering & Displays
DESCRIPTION:68. Measurement of the Imperceptible Threshold for Color Vibra
 tion Pairs Selected by using MacAdam Ellipse\n\nWe propose an efficient me
 thod to find color vibration pairs that are imperceptible to the human eye
  based on the MacAdam ellipse. We selected eight sRGB colors for experimen
 ts, conducting the experiment for establishing amplitude thresholds for fl
 icker-free perception, and providing guidelines for ...\n\n\nShingo Hattor
 i (Cluster Metaverse Lab, University of Tsukuba); Yuichi Hiroi (Cluster Me
 taverse Lab); and Takefumi Hiraki (Cluster Metaverse Lab, University of El
 ectro-Communications)\n---------------------\n66. Gabor Splatting for High
 -Quality Gigapixel Image Representations\n\nWe introduce Gabor splatting, 
 a periodic extension of Gaussian splatting which results in higher reconst
 ruction quality per-parameter for gigapixel images as compared to Gaussian
  splatting and often I-NGP.\n\n\nSkylar Wurster (Ohio State University), R
 an Zhang (Tencent PCG), and Changxi Zheng (Columbia University)\n---------
 ------------\n61. Amplify AR HUD User-Experience with Real-World Sunlight 
 Simulation in Virtual  Scene\n\nThis poster introduces the concept of real
 -world sunlight simulation in virtual scene for AR HUD application. We uti
 lize GPS and Solar Azimuth Formula in order to align the virtual source of
  light with physical sunlight direction. By placing virtual objects under 
 the same condition of real-world sun...\n\n\nEun Hye Kim, Hyocheol Ro, and
  Hyunjin Park (Hyundai Mobis)\n---------------------\n62. Denoising Monte 
 Carlo Renders with Diffusion Models\n\nWe demonstrate that large-scale pre
 trained image models can solve a classic computer graphics problem: removi
 ng ray-tracing noise, and our method is competitive with state-of-the-art 
 works.\n\n\nVaibhav Vavilala, Rahul Vasanth, and David Forsyth (University
  of Illinois Urbana-Champaign)\n---------------------\n63. Development of 
 a stereoscopic projection mapping system using a small mobile robot\n\nWe 
 have developed a projection mapping system using a small mobile robot. Thi
 s system incorporates a projector inside the robot, and projects images on
 to the floor while moving. When the system detects a person, it stops movi
 ng and projects stereoscopic images for the person while facing them.\n\n\
 nAzumi Katayama and Shinji Mizuno (Aichi Institute of Technology) and Kenj
 i Funahashi (Nagoya Institute of Technology)\n---------------------\n67. G
 eometry enhanced 3D Gaussian Splatting for high quality deferred rendering
 \n\nWe proposed a novel Geometry-enhanced 3D Gaussian Splatting (GS) metho
 d and developed a deferred rendering pipeline for its rasterization, which
  can effectively generate real-time complex illumination effects with high
 -precision depth and normal information, and have applied it to XR/VR appl
 ications...\n\n\nshuo wang, Cong Xie, Shengdong Wang, and Shaohui Jiao (By
 teDance Inc.)\n---------------------\n70. Projecting Radiance Fields to Me
 sh Surfaces with Local Space Texture Mapping\n\nRadiance fields produce hi
 gh fidelity images with high rendering speed, but are difficult to manipul
 ate. We perform avatar texture transfer by combining benefits from radianc
 e fields and mesh surfaces. The source is represented using 3D Gaussian Sp
 latter, then Gaussians projected onto target mesh. T...\n\n\nAdrian Xuan W
 ei Lim (Roblox); Lynnette Hui Xian Ng (Carnegie Mellon University); and Ni
 cholas Kyger, Tomo Michigami, and Faraz Baghernezhad (Roblox)\n-----------
 ----------\n65. Expansive Field-of-View Head-Mounted Display based on Dyna
 mic Projection Mapping\n\nIn this study, we propose a method for extending
  the peripheral field of view of conventional head-mounted displays (HMDs)
  based on dynamic projection mapping. External projectors are used to dyna
 mically project images onto lightweight peripheral screens attached to the
  periphery of the HMD.\n\n\nNaoki Hashimoto and Kazuto Saito (University o
 f Electro-Communications)\n---------------------\n60. A Surface-based Appe
 arance Model for Pennaceous Feathers\n\nWe propose a weighted BSDF of the 
 key biological structures of a feather such as the barbs and barbules base
 d on an analytical masking term derived from elliptical-cylinders fibers. 
 Our model accounts for both pigmentation and non iridescent structural col
 oration approximated by a diffuse medulla in...\n\n\nJuan Raul Padron Grif
 fe and Dario Lanza (Universidad de Zaragoza); Adrian Jarabo (Universidad d
 e Zaragoza, Meta Reality Labs); and Adolfo Muñoz (Universidad de Zaragoza)
 \n---------------------\n64. Distance-adaptive unsupervised CNN model for 
 computer-generated holography\n\nWe propose a CNN model for CGH synthesis 
 that allows specifying not only target image but also propagation distance
 . Our model demonstrates comparable performance to traditional fixed-dista
 nce methods and achieves practical generation accuracy and speed even when
  the propagation distance is changed,...\n\n\nYuto Asano, Kenta Yamamoto, 
 Tatsuki Fushimi, and Yoichi Ochiai (University of Tsukuba)\n--------------
 -------\n69. PictorialAttributes: Depicting Multiple Attributes with Reali
 stic Imaging\n\nTraditional visualizations often use abstract graphics, li
 miting understanding and memorability. Existing methods for pictorial visu
 alization are more engaging, but often create disjointed compositions. To 
 address this, we propose PictorialAttributes, a technique utilizing LLMs a
 nd diffusion models ...\n\n\nOmer Dahary (Tel Aviv University), Min Lu (Sh
 enzhen University), and Or Patashnik and Daniel Cohen-Or (Tel Aviv Univers
 ity)\n\nRegistration Category: Full Conference, Full Conference Supporter,
  Experience, Exhibitor Full Conference, Exhibitor Experience
END:VEVENT
END:VCALENDAR
