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:20260805T205452Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260721T090000
DTEND;TZID=America/Los_Angeles:20260721T103000
UID:siggraph_SIGGRAPH 2026_sess150@linklings.com
SUMMARY:Video Gen & Camera Control
DESCRIPTION:Video Analysis and Generation via a Semantic Progress Function
 \n\nThis paper introduces a Semantic Progress Function - a one-dimensional
  representation capturing the semantic pace of a given video. Building on 
 this, a semantic linearization procedure is introduced to retime sequences
  and control the rate at which semantic change unfolds, yielding smoother,
  more co...\n\n\nGal Metzer and Sagi Polaczek (Tel Aviv University), Arash
  Mahdavi-Amiri (Simon Fraser University), and Raja Giryes and Daniel Cohen
 -Or (Tel Aviv University)\n---------------------\nGo-with-the-Track: Video
  Compositing and Motion Control with Point Tracking\n\nWe present Go-with-
 the-Track, a video generation framework conditioned on multiple reference 
 images and point-tracks that jointly anchor the generated frames and the r
 eferences. Our approach enables precise control over motion and multi-refe
 rence compositing, unlocking a wide range of applications, ...\n\n\nKoichi
  Namekata (Eyeline Labs, University of Oxford); Yash Kant (Eyeline Labs, N
 etflix); Zhizheng Liu (Eyeline Labs; University of California, Los Angeles
 ); Ryan Burgert (Eyeline Labs, Stony Brook University); Yuancheng Xu (Eyel
 ine Labs, Netflix); Kuan Heng Lin (Eyeline Labs, Columbia University); Emm
 ett Steven (Netflix); Julien Philip and Li Ma (Eyeline Labs); Andrea Vedal
 di (University of Oxford); and Paul Debevec and Ning Yu (Eyeline Labs, Net
 flix)\n---------------------\nReRoPE: Repurposing RoPE for Relative Camera
  Control\n\nReRoPE is a plug-and-play framework for controllable video gen
 eration that achieves precise camera control by injecting relative pose in
 formation into the underutilized low-frequency bands of standard Rotary Po
 sitional Embeddings (RoPE).\n\n\nChunyang Li, Yuanbo Yang, Jiahao Shao, an
 d Hongyu Zhou (Zhejiang University); Katja Schwarz (Independent); and Yiyi
  Liao (Zhejiang University)\n---------------------\nFreeOrbit4D: Training-
 Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Comp
 lete 4D Reconstruction\n\nFreeOrbit4D is a training-free framework for cam
 era redirection from monocular videos. By decoupling foreground and backgr
 ound reconstruction and completing foreground geometry via multi-view diff
 usion, it builds a foreground-complete 4D proxy that guides video generati
 on, enabling faithful and temp...\n\n\nWei Cao and Hao Zhang (University o
 f Illinois Urbana-Champaign); Fengrui Tian (University of Pennsylvania); Y
 ulun Wu, Yingying Li, and Shenlong Wang (University of Illinois Urbana-Cha
 mpaign); Ning Yu (Eyeline Labs, Netflix); and Yaoyao Liu (University of Il
 linois Urbana-Champaign)\n---------------------\nUCM: Unified Modeling of 
 Camera Control and Memory with Time-aware Positional Encoding Warping for 
 World Models\n\nWe propose UCM, a novel framework for the unified modeling
  of long-term scene consistency and camera controllability in video genera
 tion-based world models. Trained on over 500K monocular videos, UCM achiev
 es high-fidelity world exploration capability with excellent generalizabil
 ity to open-world en...\n\n\nTian-Xing Xu and Zi-Xuan Wang (Tsinghua Unive
 rsity), Guangyuan Wang and Li Hu (Alibaba Group), Zhongyi Zhang (Universit
 y of Science and Technology of China), Peng Zhang and Bang Zhang (Alibaba 
 Group), and Song-Hai Zhang (Tsinghua University)\n---------------------\nC
 ameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Cam
 era-Controlled Video Generation\n\nCameraSquad is a multi-trajectory camer
 a control framework that supports both single-trajectory and parallel mult
 i-trajectory video generation. By decoupling content and camera control me
 chanisms and using a dual-mode cross-view attention mechanism, it ensures 
 viewpoint consistency and camera contro...\n\n\nZhufeng Xu and Xuan Gao (I
 nstitute of Computing Technology, Chinese Academy of Sciences; University 
 of Chinese Academy of Sciences); Bailin Deng (School of Computer Science a
 nd Informatics, Cardiff University); Yikang Ding, Xiaoqiang Liu, Haoxian Z
 hang, and Pengfei Wan (Kling Team, Kuaishou Technology); Hongbo Fu (The Ho
 ng Kong University of Science and Technology); and Lin Gao (Institute of C
 omputing Technology, Chinese Academy of Sciences; University of Chinese Ac
 ademy of Sciences)\n---------------------\nVideo Gen & Camera Control - In
 teractive Discussion\n\nAfter the summary presentations, attendees will pa
 rticipate in an interactive discussion. Outside the room will be a series 
 of poster boards for authors to gather around with the audience. Authors a
 re invited to bring any material related to their paper that could instiga
 te further conversation such...\n\n\nInterest Area: Research & Education\n
 \nKeyword: Artificial Intelligence/Machine Learning, Generative AI\n\nRegi
 stration Category: Full Conference Supporter, Full Conference\n\nSession C
 hair: Felix Heide (Princeton University, Torc Robotics)
END:VEVENT
END:VCALENDAR