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:20260805T205515Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260720T140000
DTEND;TZID=America/Los_Angeles:20260720T153000
UID:siggraph_SIGGRAPH 2026_sess156@linklings.com
SUMMARY:Video Generation
DESCRIPTION:MV-S2V: Multi-View Subject-Consistent Video Generation\n\nMV-S
 2V is the first work to explore video generation with multi-view subject c
 onsistency. It presents a simple yet effective framework, including a tail
 ored data curation pipeline and a Temporally-Shifted RoPE (TS-RoPE) specia
 lly designed for multi-view reference conditioning, achieving superior 3D 
 ...\n\n\nZiyang Song (The Hong Kong Polytechnic University), Xinyu Gong (T
 he University of Texas at Austin), Bangya Liu (University of Wisconsin-Mad
 ison), and Zelin Zhao (Georgia Institute of Technology)\n-----------------
 ----\nOmniRoam: World Wandering via Long-Horizon Panoramic Video Generatio
 n\n\nThis work introduces a controllable panoramic video generation framew
 ork designed for long-horizon scene wandering. It utilizes a global-to-loc
 al preview-and-refine pipeline to synthesize high-fidelity, spatially and 
 temporally coherent panoramic videos from a single input panoramic image o
 r video.\n\n\nYuheng Liu (University of California Irvine); Xin Lin (Unive
 rsity of California San Diego); Xinke Li (City University of Hong Kong); B
 aihan Yang (University of California San Diego); Chen Wang (University of 
 Pennsylvania); Kalyan Sunkavalli, Yannick Hold-Geoffroy, Hao Tan, and Kai 
 Zhang (Adobe Research); Xiaohui Xie (University of California Irvine); and
  Zifan Shi and Yiwei Hu (Adobe Research)\n---------------------\nActCam: Z
 ero-Shot Joint Camera and 3D Motion Control for Video Generation\n\nActCam
  is a zero-shot method providing joint control over camera trajectories an
 d character acting. It integrates into preexisting artistic workflows by l
 everaging traditional cinematography skills for fine-grained control. Requ
 iring no additional training, the framework avoids costly finetuning and..
 .\n\n\nOmar El Khalifi, Thomas Rossi, Oscar Fossey, and Thibault Fouque (K
 inetix); Ulysse Mizrahi (Kinetix, Tel Aviv University); Philip Torr (Unive
 rsity of Oxford); Ivan Laptev and Fabio Pizzati (MBZUAI); and Baptiste Bel
 lot-Gurlet (Kinetix)\n---------------------\nHL-OutPaint: Coarse-to-Fine V
 ideo Outpainting for High-Resolution Long-Range Videos\n\nWe introduce HL-
 OutPaint, a coarse-to-fine framework for high-resolution long-range video 
 outpainting. HL-OutPaint incorporates a novel global-local frame swapping 
 mechanism that enables both long-term and short-term temporal consistency.
  Experimental results show that our approach produces spatiall...\n\n\nJeo
 ngeun Park, Janghyeok Han, and Geonung Kim (POSTECH); Hyun-Seung Lee, Kyuh
 a Choi, and Youngseok Han (Visual Display Business, Samsung Electronics); 
 and Sunghyun Cho (POSTECH)\n---------------------\nUniVidX: A Unified Mult
 imodal Framework for Versatile Video Generation via Diffusion Priors\n\nUn
 iVidX is a unified multimodal video generation framework that repurposes v
 ideo diffusion priors to flexibly generate and translate across visual mod
 alities. Instantiated as UniVid-Intrinsic and UniVid-Alpha, it supports ta
 sks such as inverse rendering, relighting, matting, and inpainting, while 
 ac...\n\n\nHouyuan Chen (HKUST), Hong Li (Beihang University), Xianghao Ko
 ng (HKUST), Tianrui Zhu (Nanjing University), Shaocong Xu (Beijing Academy
  of Artificial Intelligence), Weiqing Xiao (Nanjing University), Yuwei Guo
  and Chongjie Ye (The Chinese University of Hong Kong), Lvmin Zhang (Stanf
 ord University), Hao Zhao (Tsinghua University), and Anyi Rao (HKUST)\n---
 ------------------\nVideo Generation - Interactive Discussion\n\nAfter the
  summary presentations, attendees will participate in an interactive discu
 ssion. Outside the room will be a series of poster boards for authors to g
 ather around with the audience. Authors are invited to bring any material 
 related to their paper that could instigate further conversation such...\n
 \n\nInterest Area: Research & Education\n\nKeyword: Artificial Intelligenc
 e/Machine Learning, Generative AI, Rendering\n\nRegistration Category: Ful
 l Conference Supporter, Full Conference\n\nSession Chair: Ayush Tewari (Ca
 mbridge University)
END:VEVENT
END:VCALENDAR