BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190106Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250814T090000
DTEND;TZID=America/Los_Angeles:20250814T103000
UID:siggraph_SIGGRAPH 2025_sess157@linklings.com
SUMMARY:Filtering Super-Res, & Visual Quality
DESCRIPTION:Beautiful Materials - Interactive Discussion\n\nAfter the summ
 ary presentations, attendees will participate in an interactive discussion
 . Outside the room will be a series of poster boards for authors to gather
  around with the audience. Authors are invited to bring any material relat
 ed to their paper that could instigate further conversation such...\n\n---
 ------------------\nDC-VSR: Spatially and Temporally Consistent Video Supe
 r-Resolution with Video Diffusion Prior\n\nWe propose DC-VSR, a novel vide
 o super-resolution approach based on a video diffusion prior. DC-VSR lever
 ages Spatial and Temporal Attention Propagation (SAP and TAP) to ensure sp
 atio-temporally consistent results and Detail-Suppression Self-Attention G
 uidance (DSSAG) to enhance high-frequency detai...\n\n\nJanghyeok Han, Gyu
 jin Sim, and Geonung Kim (POSTECH); Hyun-Seung Lee, Kyuha Choi, and Youngs
 eok Han (Samsung Electronics); and Sunghyun Cho (POSTECH)\n---------------
 ------\nCompensating Spatiotemporally Inconsistent Observations for Online
  Dynamic 3D Gaussian Splatting\n\nWe reveal that existing online reconstru
 ction of dynamic scenes with 3D Gaussian Splatting produces temporally inc
 onsistent results, led by inevitable noise in real-world recordings. To ad
 dress this, we decompose the rendered images into the ideal signal and the
  errors during optimization, achieving...\n\n\nYoungsik Yun, Jeongmin Bae,
  and Hyunseung Son (Yonsei University); Seoha Kim, Hahyun Lee, and Gun Ban
 g (Electronics and Telecommunications Research Institute); and Youngjung U
 h (Yonsei University)\n---------------------\nHigh-Fidelity Novel View Syn
 thesis via Splatting-Guided Diffusion\n\nWe present SplatDiff, a pixel-spl
 atting-guided diffusion model for single-image novel view synthesis (NVS).
  Leveraging pixel splatting and video diffusion, SplatDiff generates high-
 quality novel views with consistent geometry and high-fidelity details. Sp
 latDiff achieves state-of-the-art results in ...\n\n\nXiang Zhang (ETH Zür
 ich, DisneyResearch|Studios); Yang Zhang and Lukas Mehl (DisneyResearch|St
 udios); Markus Gross (ETH Zürich, DisneyResearch|Studios); and Christopher
  Schroers (DisneyResearch|Studios)\n---------------------\nFast Isotropic 
 Median Filtering\n\nThe median filter is a staple of computational image p
 rocessing. Existing efficient methods share a common flaw, which is that t
 hey use a square kernel, producing visual artifacts. Our method overcomes 
 this limitation, enabling fast and high-quality circular-kernel median fil
 tering, across multiple ...\n\n\nBen Weiss (Google Research)\n------------
 ---------\nDAM-VSR: Disentanglement of Appearance and Motion for Video Sup
 er-Resolution\n\nIn this work, we propose DAM-VSR, an appearance and motio
 n disentanglement framework for video super-resolution. Appearance enhance
 ment is achieved through reference image super-resolution, while motion co
 ntrol is achieved through video ControlNet. Additionally, we propose a mot
 ion-aligned bidirecti...\n\n\nZhe Kong (Sun Yat-sen University, Meituan); 
 Le Li (Tianjin University); Yong Zhang and Feng Gao (Meituan); Shaoshu Yan
 g (School of Artificial Intelligence, University of Chinese Academy of Sci
 ences); Tao Wang (Nanjing University); Kaihao Zhang (Harbin Institute of T
 echnology); Zhuoliang Kang and Xiaoming Wei (Meituan); Guanying Chen (Sun 
 Yat-sen University); and Wenhan Luo (The Hong Kong University of Science a
 nd Technology)\n---------------------\nA Fast Parallel Median Filtering Al
 gorithm Using Hierarchical Tiling\n\nThis paper introduces a novel median 
 filtering algorithm, using hierarchical tiling to reduce redundant computa
 tions and achieve better complexity than prior sorting-based methods. The 
 paper discusses two implementations, for both small and larger kernel size
 s, that outperform the state of the art b...\n\n\nLouis Sugy (NVIDIA)\n\nI
 nterest Area: Research & Education\n\nRecording: Livestreamed, Not Livestr
 eamed, Recorded, Not Recorded\n\nRegistration Category: Full Conference, V
 irtual Access, Thursday\n\nSession Chair: Karol Myszkowski (Max Planck Ins
 titute for Informatics)
END:VEVENT
END:VCALENDAR