{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:08Z","timestamp":1777888628158,"version":"3.51.4"},"reference-count":60,"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\/iccv51701.2025.01566","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16861-16870","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Layered Graphic Design Generation with a Top-Down Approach"],"prefix":"10.1109","author":[{"given":"Jingye","family":"Chen","sequence":"first","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaowen","family":"Wang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanxuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Difan","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jimei","family":"Yang","sequence":"additional","affiliation":[{"name":"Runway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86334-0_36"},{"key":"ref2","article-title":"Docsynthv2: A practical autoregressive modeling for document generation","author":"Biswas","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"canva","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612275"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref7","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32249"},{"key":"ref9","article-title":"Discovering the hidden vocabulary of dalle-2","author":"Daras","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","volume-title":"flux","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"ref14","article-title":"Llms meet multimodal generation and editing: A survey","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01373"},{"key":"ref20","article-title":"Opencole: Towards reproducible automatic graphic design generation","author":"Inoue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Improving diffusion models for scene text editing with dual encoders","author":"Ji","year":"2023","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref22","article-title":"Cole: A hierarchical generation framework for graphic design","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Designedit: Multilayered latent decomposition and fusion for unified & accurate image editing","author":"Jia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19994"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755420"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097900"},{"key":"ref29","article-title":"Layoutgan: Generating graphic layouts with wireframe discriminators","author":"Li","year":"2019","journal-title":"ICLR"},{"key":"ref30","article-title":"Planning and rendering: Towards end-to-end product poster generation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Textcengen: Attention-guided text-centric background adaptation for text-to-image generation","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611930"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref35","article-title":"Glyph-byt5-v2: A strong aesthetic baseline for accurate multilingual visual text rendering","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Glyphdraw: Seamlessly rendering text with intricate spatial structures in text-to-image generation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32636"},{"key":"ref38","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Posterllama: Bridging design ability of langauge model to contents-aware layout generation","author":"Seol","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00881"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00111"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02115"},{"key":"ref44","article-title":"Anytext: Multilingual visual text generation and editing","author":"Tuo","year":"2024","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_10"},{"key":"ref48","article-title":"Textctrl: Diffusion-based scene text editing with prior guidance control","author":"Zeng","year":"2024","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00664"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28550"},{"key":"ref53","article-title":"Text2layer: Layered image generation using latent diffusion model","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00716"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13576"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref57","article-title":"Harmonizing visual text comprehension and generation","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322971"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/692"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.14"}],"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\/11444504.pdf?arnumber=11444504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:52:44Z","timestamp":1777611164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01566","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}