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 3C
DTSTART;TZID=America/Denver:20240731T154500
DTEND;TZID=America/Denver:20240731T171500
UID:siggraph_SIGGRAPH 2024_sess135@linklings.com
SUMMARY:Perception, Image, Video
DESCRIPTION:Versatile Vision Foundation Model for Image and Video Coloriza
 tion\n\nIn this work, we show how a latent diffusion model, pre-trained on
  text-to-image synthesis, can be repurposed for image colorization and pro
 vide a flexible high-quality solution for a wide variety of scenarios: dir
 ect colorization with diverse results, user guidance through colors hints 
 or text prom...\n\n\nVukasin Bozic (ETH Zürich); Abdelaziz Djelouah and Ya
 ng Zhang (Disney Research Studios); Radu Timofte (University of Wurzburg);
  Markus Gross (ETH Zürich, Disney Research Studios); and Christopher Schro
 ers (Disney Research Studios)\n---------------------\nTheory of Human Tetr
 achromatic Color Experience and Printing\n\nWe apply d-dimensional color t
 heory to compute the predicted hue sphere of human tetrachromatic color sp
 ace for the first time and derive the ideal, CMY-equivalent, tetrachromati
 c printing primaries. Our prototype tetrachromatic printer utilizes four s
 elected fountain pen inks to print color tests t...\n\n\nJessica Lee, Nich
 olas Jennings, Varun Srivastava, and Ren Ng (University of California Berk
 eley)\n---------------------\nColorVideoVDP: A Visual Difference Predictor
  for Image, Video, and Display Distortions\n\nColorVideoVDP is a different
 iable image and video quality metric that models human color and spatiotem
 poral vision. It is targeted and calibrated to assess image distortions du
 e to AR/VR display technologies and video streaming, and it can handle bot
 h SDR and HDR content.\n\n\nRafal K. Mantiuk, Param Hanji, and Maliha Ashr
 af (University of Cambridge) and Yuta Asano and Alexandre Chapiro (Meta)\n
 ---------------------\nLearning Images Across Scales Using Adversarial Tra
 ining\n\nWe propose a novel paradigm to learn a scale space from an unstru
 ctured image collection using adversarial training. Enabling zoom-in facto
 rs of 256x, our approach can be used to train a multiscale generative mode
 l and for reconstructions of scale spaces from unstructured patches.\n\n\n
 Krzysztof Wolski, Adarsh Djeacoumar, Alireza Javanmardi, Hans-Peter Seidel
 , and Christian Theobalt (Max Planck Institute for Informatics); Guillaume
  Cordonnier (INRIA, Université Côte d'Azur); Karol Myszkowski (Max Planck 
 Institute for Informatics); George Drettakis (INRIA, Université Côte d'Azu
 r); Xingang Pan (Nanyang Technological University); and Thomas Leimkühler 
 (Max Planck Institute for Informatics)\n---------------------\nSelf-Superv
 ised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit V
 ideo?\n\nWe present a self-supervised approach that generates an HDR video
  from a single input SDR video without requiring HDR/SDR datasets for trai
 ning. Results are comparable and frequently better than other state-of-the
 -art methods.\n\n\nFrancesco Banterle (ISTI CNR); Demetris Marnerides, Tho
 mas Bashford-Rogers, and Kurt Debattista (University of Warwick  WMG, Warw
 ick Manufacturing Group); and Francesco Banterle\n---------------------\nP
 erception, Image, Video - Interactive Discussion\n\nAfter the summary pres
 entations, attendees will participate in an interactive discussion. Distri
 buted around the room will be a series of poster boards for authors to gat
 her around with the audience. Authors are invited to bring any material re
 lated to their paper that could instigate further conver...\n\n-----------
 ----------\nAnalogist: Out-of-the-box Visual In-context Learning With Imag
 e Diffusion Model\n\nAnalogist is a novel visual In-context Learning appro
 ach combining visual and textual prompts with a diffusion model. It introd
 uces self-attention cloning and cross-attention masking to enhance analogy
  accuracy, offering a flexible, out-of-the-box solution that outperforms e
 xisting methods without n...\n\n\nZheng Gu (Nanjing University, City Unive
 rsity of Hong Kong); Shiyuan Yang (Tianjin University, City University of 
 Hong Kong); Jing Liao (City University of Hong Kong); and Jing Huo and Yan
 g Gao (Nanjing University)\n\nInterest Area: Research & Education\n\nRegis
 tration Category: Full Conference, Full Conference Supporter, Virtual Acce
 ss, Exhibitor Full Conference, Wednesday\n\nSession Chair: Angela Dai (Tec
 hnical University of Munich)
END:VEVENT
END:VCALENDAR