BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030440Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T104000
DTEND;TZID=Asia/Hong_Kong:20251216T114500
UID:siggraphasia_SIGGRAPH Asia 2025_sess117@linklings.com
SUMMARY:Computational Photography & Cameras
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nCameraVDP: Perceptual Display As
 sessment with Uncertainty Estimation via Camera and Visual Difference Pred
 iction\n\nAccurate measurement of images produced by electronic displays i
 s critical for the evaluation of both traditional and computational displa
 ys. Traditional display measurement methods based on sparse radiometric sa
 mpling and fitting a model are inadequate for capturing spatially varying 
 display artifa...\n\n\nYancheng Cai (University of Cambridge), Robert Wana
 t (LG Electronics North America), and Rafal Mantiuk (University of Cambrid
 ge)\n---------------------\nLearning to Refocus with Video Diffusion Model
 s\n\nFocus is a cornerstone of photography, yet autofocus systems often fa
 il to capture the intended subject, and users frequently wish to adjust fo
 cus after capture. We introduce a novel method for realistic post-capture 
 refocusing using video diffusion models. From a single defocused image, ou
 r approac...\n\n\nSaiKiran Tedla (Adobe, York University) and Zhoutong Zha
 ng, Xuaner Zhang, and Shumian Xin (Adobe)\n---------------------\nGenerati
 ng the Past, Present and Future from a Motion-Blurred Image\n\nWe seek to 
 answer the question: what can a motion-blurred image reveal about a scene'
 s past, present, and future? Although motion blur obscures image details a
 nd degrades visual quality, it also encodes information about scene and ca
 mera motion during an exposure. Previous techniques leverage this i...\n\n
 \nSaiKiran Tedla (York University); Kelly Zhu (University of Toronto, Vect
 or Institute); Trevor Canham (York University); Felix Taubner (University 
 of Toronto, Vector Institute); Michael S. Brown (York University); and Kir
 iakos N. Kutulakos and David B. Lindell (University of Toronto, Vector Ins
 titute)\n---------------------\nDiffCamera: Arbitrary Refocusing on Images
 \n\nThe depth-of-field (DoF) effect, which introduces aesthetically pleasi
 ng blur, enhances photographic quality but is fixed and difficult to modif
 y once the image has been created. This becomes problematic when the appli
 ed blur is undesirable (e.g., the subject is out of focus).\nTo address th
 is, we pr...\n\n\nYiyang Wang and Xi Chen (The University of Hong Kong), X
 iaogang Xu (The Chinese University of Hong Kong), Yu Liu (Tongyi Lab), and
  Hengshuang Zhao (The University of Hong Kong)\n---------------------\nAut
 omated Design of Compound Lenses with Discrete-Continuous Optimization\n\n
 We introduce a method that automatically and jointly updates both continuo
 us and discrete parameters of a compound lens design, to improve its perfo
 rmance in terms of sharpness, speed, or both. Previous methods for compoun
 d lens design use gradient-based optimization to update continuous paramet
 ers ...\n\n\nArjun Teh (Carnegie Mellon University), Delio Vicini and Bern
 d Bickel (Google Inc.), and Ioannis Gkioulekas and Matthew O'Toole (Carneg
 ie Mellon Uniersity)\n---------------------\nUltraZoom: Generating Gigapix
 el Images from Regular Photos\n\nWe present UltraZoom, a system for genera
 ting gigapixel-resolution images of objects from casually captured inputs,
  such as handheld phone photos. Given a full-shot image (global, low-detai
 l) and one or more close-ups (local, high-detail), UltraZoom upscales the 
 full image to match the fine detail a...\n\n\nJingwei Ma, Vivek Jayaram, B
 rian Curless, Ira Kemelmacher-Shlizerman, and Steven Seitz (University of 
 Washington)\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nSession Chair: Qiang Fu (King Abdullah University of Science and Technol
 ogy (KAUST))
END:VEVENT
END:VCALENDAR