{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T13:41:49Z","timestamp":1770990109861,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160305"],"award-info":[{"award-number":["2022ZD0160305"]}]},{"name":"ByteDance","award":["CT20240607105793"],"award-info":[{"award-number":["CT20240607105793"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3595880","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:06:54Z","timestamp":1754417214000},"page":"11040-11050","source":"Crossref","is-referenced-by-count":1,"title":["InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6872-7471","authenticated-orcid":false,"given":"Chenguo","family":"Lin","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Lin","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-012X","authenticated-orcid":false,"given":"Panwang","family":"Pan","sequence":"additional","affiliation":[{"name":"PICO AI Group, ByteDance, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5092-8657","authenticated-orcid":false,"given":"Xuanyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"PICO AI Group, ByteDance, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7815-3750","authenticated-orcid":false,"given":"Yadong","family":"Mu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3381866"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01760"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611800"},{"key":"ref12","article-title":"LayoutGPT: Compositional visual planning and generation with large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14927"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"ref15","first-page":"12013","article-title":"ATISS: Autoregressive transformers for indoor scene synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paschalidou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548332"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref18","article-title":"Clip-layout: Style-consistent indoor scene synthesis with semantic furniture embedding","author":"Liu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01938"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"ref22","article-title":"CommonScenes: Generating commonsense 3D indoor scenes with scene graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhai"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref24","article-title":"OpenShape: Scaling up 3D shape representation towards open-world understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref25","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref26","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref27","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237577"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00662"},{"key":"ref33","article-title":"Learning deep generative models of graphs","author":"Li","year":"2018"},{"key":"ref34","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref35","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475497"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/692"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.226"},{"key":"ref42","first-page":"5708","article-title":"GraphRNN: Generating realistic graphs with deep auto-regressive models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01605"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_41"},{"key":"ref45","first-page":"22168","article-title":"VARSCENE: A deep generative model for realistic scene graph synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref46","first-page":"1","article-title":"MolGAN: An implicit generative model for small molecular graphs","volume-title":"Proc. ICML 2018 Workshop Theor. Found. Appl. Deep Generative Models","author":"De Cao"},{"key":"ref47","first-page":"15159","article-title":"SPECTRE: Spectral conditioning helps to overcome the expressivity limits of one-shot graph generators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Martinkus"},{"key":"ref48","first-page":"4474","article-title":"Permutation invariant graph generation via score-based generative modeling","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Niu"},{"key":"ref49","first-page":"10362","article-title":"Score-based generative modeling of graphs via the system of stochastic differential equations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jo"},{"key":"ref50","first-page":"1","article-title":"DiGress: Discrete denoising diffusion for graph generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vignac"},{"key":"ref51","first-page":"17391","article-title":"Autoregressive diffusion model for graph generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8696-5_5"},{"key":"ref53","article-title":"LIC-GAN: Language information conditioned graph generative GAN model","author":"Lo","year":"2023"},{"key":"ref54","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref55","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref56","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref57","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hoogeboom"},{"key":"ref58","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Austin"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref60","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref61","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref65","first-page":"1","article-title":"A generalization of transformer networks to graphs","volume-title":"Proc. AAAI Workshop Deep Learn. Graphs: Methods Appl.","author":"Dwivedi"},{"key":"ref66","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref67","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref68","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref69","article-title":"NAP: Neural 3D articulation prior","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref71","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref72","first-page":"1","article-title":"The role of ImageNet classes in Fr\u00e9chet inception distance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kynk\u00e4\u00e4nniemi"},{"key":"ref73","first-page":"1","article-title":"Demystifying MMD GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bi\u0144kowski"},{"key":"ref74","volume-title":"Blender - A 3D Modelling and Rendering Package","author":"Community","year":"2018"},{"key":"ref75","first-page":"1","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref76","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"ref79","article-title":"Paper2Poster: Towards multimodal poster automation from scientific papers","author":"Pang","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11114812.pdf?arnumber=11114812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:47:50Z","timestamp":1762408070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":79,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3595880","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}