BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163716Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T114000
DTEND;TZID=Australia/Melbourne:20231214T124000
UID:siggraphasia_SIGGRAPH Asia 2023_sess170@linklings.com
SUMMARY:Magic Diffusion Model
DESCRIPTION:Low-Light Image Enhancement with Wavelet-based Diffusion Model
 s\n\nDiffusion models have achieved promising results in image restoration
  tasks, yet suffer from time-consuming, excessive computational resource c
 onsumption, and unstable restoration. To address these issues, we propose 
 a robust and efficient Diffusion-based Low-Light image enhancement approac
 h, dubbed...\n\n\nHai Jiang (Sichuan University); Ao Luo and Haoqiang Fan 
 (Megvii); Songchen Han (Sichuan University); and Shuaicheng Liu (Universit
 y of Electronic Science and Technology of China, Megvii)\n----------------
 -----\nExample-Based Sampling with Diffusion Models\n\nMuch effort has bee
 n put into developing samplers with specific properties, such as producing
  blue noise, low-discrepancy, lattice or Poisson disk samples. These sampl
 ers can be slow if they rely on optimization processes, may rely on a wide
  range of numerical methods, are not always differentiable....\n\n\nBastie
 n Doignies (Université Claude Bernard Lyon, CNRS); Nicolas Bonneel, David 
 Coeurjolly, and Julie Digne (CNRS, LIRIS); Loïs Paulin (Université Claude 
 Bernard Lyon / CNRS, Adobe); and Jean-Claude Iehl and Victor Ostromoukhov 
 (Université Claude Bernard Lyon, CNRS)\n---------------------\nDiffusing C
 olors: Image Colorization with Text Guided Diffusion\n\nThe colorization o
 f grayscale images is a complex and subjective task with significant chall
 enges. Despite recent progress in employing large-scale datasets with deep
  neural networks, difficulties with controllability and visual quality per
 sist. To tackle these issues, we present a novel image color...\n\n\nNir Z
 abari, Aharon Azulay, Alexey Gorkor, and Tavi Halperin (Lightricks) and Oh
 ad Fried (Reichman University)\n---------------------\nSingle-Image 3D Hum
 an Digitization with Shape-guided Diffusion\n\nWe present an approach to g
 enerate a 360-degree view of a person with a consistent, high-resolution a
 ppearance from a single input image. NeRF and its variants typically requi
 re videos or images from different viewpoints. Most existing approaches ta
 king monocular input either rely on ground-truth 3D...\n\n\nBadour AlBahar
  (Kuwait University); Shunsuke Saito, Hung-Yu Tseng, Changil Kim, and Joha
 nnes Kopf (Meta); and Jia-Bin Huang (University of Maryland)\n------------
 ---------\nEnhancing Diffusion Models with 3D Perspective Geometry Constra
 ints\n\nWhile perspective is a well-studied topic in art, it is generally 
 taken for granted in images. However, for the recent wave of high-quality 
 image synthesis methods such as latent diffusion models, perspective accur
 acy is not an explicit requirement. Since these methods are capable of out
 putting a wi...\n\n\nRishi Upadhyay and Howard Zhang (University of Califo
 rnia, Los Angeles); Yunhao Ba (University of California, Los Angeles; Sony
 ); Ethan Yang, Blake Gella, and Sicheng Jiang (University of California, L
 os Angeles); Alex Wong (Yale University); and Achuta Kadambi (University o
 f California, Los Angeles)\n\nRegistration Category: Full Access\n\nSessio
 n Chair: Xiangyu Xu (Xi'an Jiaotong University)
END:VEVENT
END:VCALENDAR