{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:46Z","timestamp":1777889446579,"version":"3.51.4"},"reference-count":71,"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\/iccv51701.2025.01677","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18046-18057","source":"Crossref","is-referenced-by-count":0,"title":["Laconic: A 3D Layout Adapter for Controllable Image Creation"],"prefix":"10.1109","author":[{"given":"L\u00e9opold","family":"Maillard","sequence":"first","affiliation":[{"name":"Ecole Polytechnique, IP Paris,LIX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Durand","sequence":"additional","affiliation":[{"name":"Dassault Systemes"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrien Ramanana","family":"Rahary","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique, IP Paris,LIX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maks","family":"Ovsjanikov","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique, IP Paris,LIX"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657525"},{"key":"ref3","article-title":"Demystifying MMD GANs","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bi\u0144kowski"},{"key":"ref4","first-page":"4217","article-title":"Generative novel view synthesis with 3d-aware diffusion models","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Eric"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"ref7","article-title":"Build-a-scene: Interactive 3d layout control for diffusion-based image generation","volume-title":"In The Thirteenth International Conference on Learning Representations (ICLR)","author":"Eldesokey"},{"key":"ref8","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning (ICML)","author":"Esser"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00069"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref11","article-title":"CAT3d: Create anything in 3d with multi-view diffusion models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Gao"},{"key":"ref12","first-page":"11808","article-title":"Nerfdiff: Single-image view synthesis with nerf-guided distillation from 3d-aware diffusion","volume-title":"In International Conference on Machine Learning (ICML)","author":"Gu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref14","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","volume-title":"In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Edward"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref21","article-title":"Controllable text-to-image generation","volume":"32","author":"Li","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref25","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Lipman"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","article-title":"SINGAPO: Single image controlled generation of articulated parts in objects","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Liu"},{"key":"ref28","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1035"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3467"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0155"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref34","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning (ICML)","author":"Quinn Nichol"},{"key":"ref35","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00662"},{"key":"ref38","article-title":"Benchmark for compositional text-toimage synthesis","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Huk Park"},{"key":"ref39","first-page":"12013","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"34","author":"Paschalidou","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref42","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Poole"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language super-vision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref50","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"ref52","article-title":"MVDream: Multi-view diffusion for 3d generation","volume-title":"In The Twelfth International Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref53","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Singer"},{"key":"ref54","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2229"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_25"},{"key":"ref59","article-title":"Semantic image synthesis via diffusion models","volume-title":"arXiv preprint","author":"Wang","year":"2022"},{"key":"ref60","article-title":"Novel view synthesis with diffusion models","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Watson"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref62","article-title":"Neural assets: 3d-aware multi-object scene synthesis with image diffusion models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Wu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2608"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref66","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref68","article-title":"Commonscenes: Generating commonsense 3d indoor scenes with scene graphs","volume":"36","author":"Zhai","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"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\/11443638.pdf?arnumber=11443638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:55Z","timestamp":1777612435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01677","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}