{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:26:00Z","timestamp":1780392360296,"version":"3.54.1"},"reference-count":90,"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"}],"funder":[{"DOI":"10.13039\/100000006","name":"office of Naval Research","doi-asserted-by":"publisher","award":["N000142412696"],"award-info":[{"award-number":["N000142412696"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02324","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25062-25072","source":"Crossref","is-referenced-by-count":2,"title":["Baking Gaussian Splatting Into Diffusion Denoiser for Fast and Scalable Single-Stage Image-to-3D Generation and Reconstruction"],"prefix":"10.1109","author":[{"given":"Yuanhao","family":"Cai","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixun","family":"Liang","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengwei","family":"Ren","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fujun","family":"Luan","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soo Ye","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Zhou","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2002.003.0004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"ref3","article-title":"Denoising diffusion via image-based rendering","author":"Anciukevicius","year":"2024","journal-title":"ICLR"},{"key":"ref4","article-title":"Video generation models as world simulators","author":"Brooks","journal-title":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02124"},{"key":"ref8","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref15","article-title":"Lightgaussian: Unbounded 3d gaussian compression with 15 x reduction and 200+fps","author":"Fan","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Large spatial model: End-to-end unposed images to semantic 3d","author":"Fan","year":"2024","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv"},{"key":"ref18","article-title":"Nerfdiff: Single-image view synthesis with nerf-guided distillation from 3d-aware diffusion","volume-title":"ICML","author":"Gu","year":"2023"},{"key":"ref19","article-title":"3dgen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02202"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00642"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00509"},{"key":"ref25","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","article-title":"Evo-nerf: Evolving nerf for sequential robot grasping of transparent objects","author":"Kerr","year":"2022","journal-title":"CoRL"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref30","first-page":"1","article-title":"Rt-nerf: Real-time on-device neural radiance fields towards immersive ar\/vr rendering","volume-title":"Proceedings of the 41st IEEE\/ACM International Conference on Computer-Aided Design","author":"Li","year":"2022"},{"key":"ref31","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02045"},{"key":"ref35","article-title":"Diffsplat: Repurposing image diffusion models for scalable 3d gaussian splat generation","author":"Lin","year":"2025","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref37","article-title":"Openillumination: A multi-illumination dataset for inverse rendering evaluation on real objects","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref40","article-title":"Animatable 3d gaussian: Fast and highquality reconstruction of multiple human avatars","author":"Liu","year":"2023","journal-title":"ACM MM"},{"key":"ref41","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2024","journal-title":"CVPR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref43","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00044"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00081"},{"key":"ref47","article-title":"Gsd: View-guided gaussian splatting diffusion for 3d reconstruction","author":"Mu","year":"2024","journal-title":"ECCV"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref49","article-title":"Mixed precision training","author":"Narang","year":"2018","journal-title":"ICLR"},{"key":"ref50","article-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Autodecoding latent 3d diffusion models","author":"Ntavelis","year":"2023","journal-title":"NeurIPS"},{"key":"ref52","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref54","article-title":"Neue Geometrie des Raumes gegrundet auf die Betrachtung der geraden Linie als Raumelement von Julius Pluecker","author":"Pl\u00fccker","journal-title":"Teubner, 1869"},{"key":"ref55","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref61","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref62","article-title":"Light field networks: Neural scene representations with single-evaluation rendering","author":"Sitzmann","year":"2021","journal-title":"NeurIPS"},{"key":"ref63","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref64","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00814"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"ref68","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Lgm: Large multi-view gaussian model for high-resolution 3d content creation","author":"Tang","year":"2024","journal-title":"ECCV"},{"key":"ref70","article-title":"Vistadream: Sampling multiview consistent images for single-view scene reconstruction","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01920"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00420"},{"key":"ref75","article-title":"Dmv3d: Denoising multi-view diffusion using 3d large reconstruction model","author":"Xu","year":"2024","journal-title":"ICLR"},{"key":"ref76","article-title":"Gs-slam: Dense visual slam with 3d gaussian splatting","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_15"},{"key":"ref79","article-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors","author":"Yi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02043"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref83","article-title":"Mvimgnet: A largescale dataset of multi-view images","author":"Yu","year":"2023","journal-title":"CVPR"},{"key":"ref84","article-title":"Gaussian-slam: Photo-realistic dense slam with gaussian splatting","author":"Yugay","year":"2023","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Gaussiancube: Structuring gaussian splatting using optimal transport for 3d generative modeling","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_41"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01717"},{"key":"ref89","article-title":"Diffgs: Functional gaussian splatting diffusion","author":"Zhou","year":"2024","journal-title":"NeurIPS"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11445669.pdf?arnumber=11445669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:07Z","timestamp":1777530127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02324","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}