{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:04Z","timestamp":1784268544889,"version":"3.55.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01835","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19731-19741","source":"Crossref","is-referenced-by-count":7,"title":["LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Yiren","family":"Song","sequence":"first","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danze","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/122718.122757"},{"key":"ref2","first-page":"16351","article-title":"Deepsvg: A hierarchical generative network for vector graphics animation","volume":"33","author":"Carlier","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Pixart\\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Transanimate: Taming layer diffusion to generate rgba video","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/7529.8927"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3592128"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_35"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0376"},{"key":"ref9","article-title":"RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers","author":"Gong","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Google","volume-title":"Noto Emoji Fonts"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01774"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27987"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611766"},{"key":"ref16","article-title":"Photodoodle: Learning artistic image editing from few-shot pairwise data","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"ref18","article-title":"Black Forest Labs","volume-title":"FLUX","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417871"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00653"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00802"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i9.37697"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01583"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref26","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00726"},{"key":"ref29","article-title":"Starvector: Generating scalable vector graphics code from images","author":"Rodriguez","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref31","article-title":"WordCon: Word-level Typography Control in Scene Text Rendering","author":"Shi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"FonTS: Text Rendering with Typography and Style Controls","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_39"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548146"},{"key":"ref35","article-title":"ProcessPainter: Learn Painting Process from Sequence Data","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Omniconsistency: Learning style-agnostic consistency from paired stylization data","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25326"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00287"},{"key":"ref42","article-title":"2022. CLIPFont: Text Guided Vector WordArt Generation","volume-title":"BMVC","author":"Song"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref44","article-title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00439"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref47","article-title":"GRID: Visual Layout Generation","author":"Wan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Instantid: Zero-shot identitypreserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480488"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00724"},{"key":"ref51","article-title":"DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"IconShop: Text-Based Vector Icon Synthesis with Autoregressive Transformers","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01815"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01815"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0698"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"ref57","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3658204"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00771"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447042"},{"key":"ref62","article-title":"Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01814"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33123"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444519.pdf?arnumber=11444519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:43Z","timestamp":1777612003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01835","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}