{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T21:09:19Z","timestamp":1784149759448,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402417"],"award-info":[{"award-number":["62402417"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273302"],"award-info":[{"award-number":["62273302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036009"],"award-info":[{"award-number":["62036009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936006"],"award-info":[{"award-number":["61936006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Ningbo","award":["2024Z115"],"award-info":[{"award-number":["2024Z115"]}]},{"name":"Key Research and Development Program of Ningbo","award":["2025Z035"],"award-info":[{"award-number":["2025Z035"]}]},{"name":"Yongjiang Talent Introduction Program","award":["2023A-197-G"],"award-info":[{"award-number":["2023A-197-G"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3706287","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:42:29Z","timestamp":1782762149000},"page":"7249-7260","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7336-4509","authenticated-orcid":false,"given":"Linxuan","family":"Xia","sequence":"first","affiliation":[{"name":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-193X","authenticated-orcid":false,"given":"Boxi","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Software, Zhejiang University, Ningbo, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Yang","sequence":"additional","affiliation":[{"name":"FiT Department, Tencent Technology (Shenzhen) Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianrun","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Software, Zhejiang University, Ningbo, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibo","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Video Rebirth, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102846"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref7","first-page":"1","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. ICLR","author":"Nichol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","article-title":"BEVControl: Accurately controlling street-view elements with multi-perspective consistency via BEV sketch layout","author":"Yang","year":"2023","journal-title":"arXiv:2308.01661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref11","first-page":"1","article-title":"MagicDrive: Street view generation with diverse 3D geometry control","volume-title":"Proc. ICLR","author":"Gao"},{"key":"ref12","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref13","article-title":"A note on the inception score","author":"Barratt","year":"2018","journal-title":"arXiv:1801.01973"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2071"},{"key":"ref16","article-title":"NuScenes: A multimodal dataset for autonomous driving","author":"Caesar","year":"2019","journal-title":"arXiv:1903.11027"},{"key":"ref17","first-page":"1","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref18","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref20","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref21","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv:2310.04378"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2026.3654412"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3639307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00428"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00844"},{"key":"ref31","article-title":"MVDream: Multi-view diffusion for 3D generation","author":"Shi","year":"2023","journal-title":"arXiv:2308.16512"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref33","first-page":"1","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref35","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022","journal-title":"arXiv:2209.14491"},{"key":"ref36","article-title":"ImageRAG: Dynamic image retrieval for reference-guided image generation","author":"Shalev-Arkushin","year":"2025","journal-title":"arXiv:2502.09411"},{"key":"ref37","article-title":"RealRAG: Retrieval-augmented realistic image generation via self-reflective contrastive learning","author":"Lyu","year":"2025","journal-title":"arXiv:2502.00848"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754727"},{"key":"ref39","article-title":"IA-T2I: Internet-augmented text-to-image generation","author":"Li","year":"2025","journal-title":"arXiv:2505.15779"},{"key":"ref40","article-title":"Cross-modal RAG: Sub-dimensional text-to-image retrieval-augmented generation","author":"Zhu","year":"2025","journal-title":"arXiv:2505.21956"},{"key":"ref41","first-page":"1","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. NeurIPS","author":"Lewis"},{"key":"ref42","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","author":"Rombach","year":"2022","journal-title":"arXiv:2207.13038"},{"key":"ref43","article-title":"KNN-diffusion: Image generation via large-scale retrieval","author":"Sheynin","year":"2022","journal-title":"arXiv:2204.02849"},{"key":"ref44","article-title":"DP-RDM: Adapting diffusion models to private domains without fine-tuning","author":"Lebensold","year":"2024","journal-title":"arXiv:2403.14421"},{"key":"ref45","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref46","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref47","article-title":"PixArt-$\\alpha$\n: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv:2310.00426"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0165"},{"key":"ref51","first-page":"1","article-title":"Assessing generative models via precision and recall","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Sajjadi"},{"key":"ref52","first-page":"7176","article-title":"Reliable fidelity and diversity metrics for generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Naeem"},{"key":"ref53","article-title":"The vendi score: A diversity evaluation metric for machine learning","author":"Friedman","year":"2022","journal-title":"arXiv:2210.02410"},{"key":"ref54","first-page":"1","article-title":"A non-parametric test to detect data-copying in generative models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Meehan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1436"},{"key":"ref56","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32469"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00819"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11585970.pdf?arnumber=11585970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:16:33Z","timestamp":1784146593000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11585970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3706287","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}