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:20260417T190049Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250813T154500
DTEND;TZID=America/Los_Angeles:20250813T173500
UID:siggraph_SIGGRAPH 2025_sess142@linklings.com
SUMMARY:Image Representation,  Editing, & Generation
DESCRIPTION:Image Representation, Editing, & Generation - Interactive Disc
 ussion\n\nAfter the summary presentations, attendees will participate in a
 n interactive discussion. Outside the room will be a series of poster boar
 ds for authors to gather around with the audience. Authors are invited to 
 bring any material related to their paper that could instigate further con
 versation such...\n\n---------------------\nIP-Composer: Semantic Composit
 ion of Visual Concepts\n\nIP-Composer is a novel, training-free method for
  compositional image generation from multiple reference images. Extending 
 IP-Adapter, it uses natural language to identify concept-specific subspace
 s in CLIP, projects input images into these subspaces to extract targeted 
 concepts, and fuses them into ...\n\n\nSara Dorfman and Dana Cohen-Bar (Te
 l Aviv University), Rinon Gal (NVIDIA), and Daniel Cohen-Or (Tel Aviv Univ
 ersity)\n---------------------\nIP-Prompter: Training-Free Theme-Specific 
 Image Generation via Dynamic Visual Prompting\n\nThis paper presents T-Pro
 mpter, a method for visually prompting generative models to enable continu
 ous image generation for specific themes, characters, and scenes. It intro
 duces Dynamic Visual Prompting to enhance generation accuracy and quality,
  outperforming existing methods in maintaining charac...\n\n\nYuxin Zhang,
  Minyan Luo, and Weiming Dong (MAIS, Institute of Automation, Chinese Acad
 emy of Sciences; School of Artificial Intelligence, University of Chinese 
 Academy of Sciences); Xiao Yang, Haibin Huang, and Chongyang Ma (ByteDance
  Inc.); Oliver Deussen (University of Konstanz); Tong-Yee Lee (National Ch
 eng-Kung University); and Changsheng Xu (MAIS, Institute of Automation, Ch
 inese Academy of Sciences; School of Artificial Intelligence, University o
 f Chinese Academy of Sciences)\n---------------------\npOps: Photo-Inspire
 d Diffusion Operators\n\npOps is a framework for learning semantic manipul
 ations in CLIP’s image embedding space. Built on a Diffusion Prior model, 
 it enables concept manipulation by training operators directly on image em
 beddings. This approach enhances semantic control and integrates easily wi
 th diffusion models for...\n\n\nElad Richardson (Tel Aviv University); Yuv
 al Alaluf (Tel Aviv University, Snap); Ali Mahdavi-Amiri (Simon Fraser Uni
 versity); and Daniel Cohen-Or (Tel Aviv University)\n---------------------
 \nPocket Time-Lapse\n\nPocket Time-Lapse is a system to record, explore an
 d visualize long-term changes in the environment, based on data that a use
 r can capture with the phone they carry. Our contributions include a proce
 ss to conveniently capture a scene, and novel techniques for registering a
 nd visualizing panoramic ti...\n\n\nEric Chen (Cornell University; Compute
 r Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts In
 stitute of Technology (MIT)) and Žiga Kovačič, Madhav Aggarwal, and Abe Da
 vis (Cornell University)\n---------------------\nInstanceGen: Image Genera
 tion with Instance-level Instructions\n\nWe propose InstanceGen - a new te
 chnique for improving Text-to-Image models ability to generate images for 
 prompts describing multiple objects, attributes and spatial relationships.
  InstanceGen requires no training or additional user inputs and achieves s
 tate-of-the art results in terms of both accu...\n\n\nEtai Sella (Tel Aviv
  University, Meta); Yanir Kleiman (Meta); and Hadar Averbuch-Elor (Cornell
  Tech)\n---------------------\nGenerating Past and Future in Digital Paint
 ing Processes\n\nA framework to generate past and future processes for dra
 wing process videos.\n\n\nLvmin Zhang and Chuan Yan (Stanford University),
  Yuwei Guo and Jinbo Xing (CUHK), and Maneesh Agrawala (Stanford Universit
 y)\n---------------------\nDreamMask: Boosting Open-vocabulary Panoptic Se
 gmentation with Synthetic Data\n\nTo address a lack of generalization to n
 ovel classes, we propose DreamMask, which systematically explores data gen
 eration in the open-vocabulary setting, and how to train the model with bo
 th real and synthetic data. It significantly simplifies the collection of 
 large-scale training data, serving as ...\n\n\nYuanpeng Tu and Xi Chen (Th
 e University of Hong Kong), Ser-Nam Lim (UCF), and Hengshuang Zhao (The Un
 iversity of Hong Kong)\n\nInterest Area: Research & Education\n\nRecording
 : Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistration C
 ategory: Full Conference, Virtual Access, Wednesday\n\nSession Chair: Vale
 ntin Deschaintre (Adobe Research)
END:VEVENT
END:VCALENDAR