{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T20:12:44Z","timestamp":1785269564889,"version":"3.55.0"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00129","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1262-1272","source":"Crossref","is-referenced-by-count":3,"title":["Mixed Diffusion for 3D Indoor Scene Synthesis"],"prefix":"10.1109","author":[{"given":"Siyi","family":"Hu","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego Martin","family":"Arroyo","sequence":"additional","affiliation":[{"name":"Google, Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Debats","sequence":"additional","affiliation":[{"name":"Google, Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Manhardt","sequence":"additional","affiliation":[{"name":"Google, Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Carlone","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Google, Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"simple-3dviz","author":"Angelos","year":"2020"},{"key":"ref2","article-title":"Structured Denoising Diffusion Models in Discrete State-Spaces","author":"Austin","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","author":"Ba","year":"2016","journal-title":"Layer Normalization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01760"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_42"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02716"},{"key":"ref9","article-title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","author":"Feng","year":"2023","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964929"},{"key":"ref11","first-page":"39897","article-title":"SceneScape: text-driven consistent scene generation","volume-title":"NeurIPS","author":"Fridman","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_21"},{"key":"ref18","author":"Hendrycks","year":"2016","journal-title":"Gaussian Error Linear Units (GELUs)"},{"key":"ref19","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"NeurIPS","volume":"33","author":"Ho","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref21","article-title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","author":"Hoogeboom","year":"2021","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00465"},{"key":"ref24","article-title":"Elucidating the Design Space of Diffusion-Based Generative Models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref25","first-page":"12104","article-title":"Training Generative Adversarial Networks with Limited Data","volume-title":"NeurIPS","author":"Karras","year":"2020"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref27","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32549"},{"key":"ref30","article-title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","volume-title":"ICLR","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00069"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964982"},{"key":"ref34","first-page":"8162","article-title":"Improved Denoising Diffusion Probabilistic Models","volume-title":"ICML","author":"Nichol"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00662"},{"key":"ref36","first-page":"12013","article-title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","volume-title":"NeurIPS","volume":"34","author":"Paschalidou","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_10"},{"key":"ref39","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3D classification and segmentation","volume-title":"CVPR","author":"Qi"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00618"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"ref44","first-page":"2256","article-title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref45","article-title":"Denoising Diffusion Implicit Models","volume-title":"ICLR","author":"Song"},{"key":"ref46","article-title":"Generative Modeling by Estimating Gradients of the Data Distribution","volume-title":"NeurIPS","volume":"32","author":"Song","year":"2019"},{"key":"ref47","first-page":"12438","article-title":"Improved Techniques for Training Score-Based Generative Models","volume-title":"NeurIPS","volume":"33","author":"Song","year":"2020"},{"key":"ref48","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","volume-title":"ICLR","author":"Song"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1944846.1944851"},{"key":"ref50","article-title":"DiffuScene: Scene Graph Denoising Diffusion Probabilistic Model for Generative Indoor Scene Synthesis","volume-title":"CVPR","author":"Tang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00558"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01492"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185552"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964981"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2417575"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref63","author":"Zhai","year":"2023","journal-title":"CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3381866"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492013.pdf?arnumber=11492013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:40Z","timestamp":1778046820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00129","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}