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:20260805T205513Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260723T090000
DTEND;TZID=America/Los_Angeles:20260723T103000
UID:siggraph_SIGGRAPH 2026_sess155@linklings.com
SUMMARY:NPR, Style &  Abstraction
DESCRIPTION:Lifting Lines and Tone: Image-Space Stylization in Path-Space\
 n\nWe present a framework for lifting image-space stylizations into path-s
 pace rendering, and demonstrate it on line and tone rendering. By construc
 ting geometric mappings between image and path space, our method preserves
  line and tone structure under complex light transport, enabling coherent,
  expres...\n\n\nRex West (Aoyama Gakuin University), Sayan Mukherjee (The 
 University of Tokyo), and Yonghao Yue (Aoyama Gakuin University)\n--------
 -------------\nAbstraction in Style: Beyond Texture and Color\n\nArtistic 
 styles often involve shape reinterpretation, not merely a change of surfac
 e appearance. Conventional style transfer methods miss this deeper abstrac
 tion behavior. We introduce Abstraction in Style (AiS), a two-stage genera
 tive framework that learns and transfers style at shape level, beyond...\n
 \n\nMin Lu and Yuanfeng He (Shenzhen University); Anthony Chen (Peking Uni
 versity); Jianhuang He and Pu Wang (Shenzhen University); Daniel Cohen-Or 
 (Tel Aviv University, Shenzhen University); and Hui Huang (Shenzhen Univer
 sity)\n---------------------\nProgressive Photorealistic Simplification\n\
 nWe introduce a method for simplifying photorealistic scenes by progressiv
 ely removing elements based on semantic importance. Our framework systemat
 ically removes elements in a hierarchical order, using generative inpainti
 ng to maintain photorealism throughout the process. This generates plausib
 le ph...\n\n\nAdi Rosenthal (Reichman University, Google); Dana Berman (Go
 ogle); Yedid Hoshen (Hebrew University of Jerusalem, Google); and Ariel Sh
 amir (Reichman University, Google)\n---------------------\nGimmBO: Interac
 tive Generative Image Model Merging via Bayesian Optimization\n\nGimmBO he
 lps users interactively explore combinations of customized image generatio
 n styles to create desired results. It replaces manual slider tuning with 
 a tailored Preferential Bayesian Optimization approach, outperforming alte
 rnatives in simulations and user studies. It further extends to combi...\n
 \n\nChenxi Liu and Selena Ling (University of Toronto) and Alec Jacobson (
 University of Toronto, Vector Institute)\n---------------------\nSemantic-
 Structural Alignment for Generative Pictorial Charts\n\nWe introduce a gen
 erative framework that transforms traditional statistical graphics into me
 morable, engaging pictorial charts. It utilizes structural alignment to an
 chor spatial layouts and semantic alignment to transfer expressive texture
 s. This ensures the resulting visuals are artistically compe...\n\n\nZhida
  Sun, Yulin Zhang, Zheng Gu, and Min Lu (Shenzhen University); Bongshin Le
 e (Yonsei University); Daniel Cohen-Or (Tel Aviv University, Shenzhen Univ
 ersity); and Hui Huang (Shenzhen University)\n---------------------\nGradi
 ent Descent in the ALPS: Abstracted Low-Poly Stylization and Fabrication\n
 \nWe generate 2D low-poly meshes that abstract images using score distilla
 tion sampling. We focus on ensuring the validity of the output mesh, quant
 ized palette colors and semantic similarity to the input. The resulting ve
 ctor images are easy to edit and fabricated as mosaics, embroidery, croche
 ting, ...\n\n\nRuben Wiersma (ETH Zurich, Adobe Research) and Alexandre Bi
 nninger, Peizhuo Li, Annika Oehri, Aviv Segall, Tanguy Magne, Danielle Lut
 erbacher, Marcel Padilla, Jing Ren, and Olga Sorkine-Hornung (ETH Zurich)\
 n---------------------\nNPR, Style & Abstraction - Interactive Discussion\
 n\nAfter the summary presentations, attendees will participate in an inter
 active discussion. Outside the room will be a series of poster boards for 
 authors to gather around with the audience. Authors are invited to bring a
 ny material related to their paper that could instigate further conversati
 on such...\n\n\nInterest Area: Research & Education\n\nKeyword: Artificial
  Intelligence/Machine Learning, Fabrication, Generative AI, Modeling, Rend
 ering\n\nRegistration Category: Full Conference Supporter, Full Conference
 \n\nSession Chair: Bohan Wang (National University of Singapore)
END:VEVENT
END:VCALENDAR