{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:18Z","timestamp":1777888878317,"version":"3.51.4"},"reference-count":89,"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\/iccv51701.2025.01570","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16904-16915","source":"Crossref","is-referenced-by-count":0,"title":["DiffSim: Taming Diffusion Models for Evaluating Visual Similarity"],"prefix":"10.1109","author":[{"given":"Yiren","family":"Song","sequence":"first","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Show Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Midjourney sref: Prompt library and examples"},{"key":"ref2","year":"2024","journal-title":"Flux. 1 AI. Flux. 1 ai"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Robust classification via a single diffusion model","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"ref9","article-title":"Transanimate: Taming layer diffusion to generate rgba video","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref11","article-title":"Wmadapter: Adding watermark control to latent diffusion models","author":"Ci","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02059"},{"key":"ref15","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref18","article-title":"Relationadapter: Learning and transferring visual relation with diffusion transformers","author":"Gong","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref21","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Idanimator: Zero-shot identity-preserving human video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0223792"},{"key":"ref24","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref28","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref29","article-title":"Photodoodle: Learning artistic image editing from few-shot pairwise data","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"1244","article-title":"Comparing higher-order spatial statistics and perceptual judgements in the stylometric analysis of art","volume-title":"2011 19th European Signal Processing Conference","author":"Hughes","year":"2011"},{"key":"ref31","article-title":"Autoregressive images watermarking through lexical biasing: An approach resistant to regeneration attack","author":"Hui","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3231558"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00676"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01611"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1780"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref38","article-title":"Image watermarks are removable using controllable regeneration from clean noise","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i9.37697"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.740"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref43","article-title":"Follow-your-creation: Empowering 4d creation through video inpainting","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref45","article-title":"Follow-your-motion: Video motion transfer via efficient spatial-temporal decoupled finetuning","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref47","article-title":"Human alignment of neural network representations","author":"Muttenthaler","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","article-title":"Dreambench++: A human-aligned benchmark for personalized image generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02895-8_36"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1998.711107"},{"key":"ref57","article-title":"Fonts: Text rendering with typography and style controls","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Wordcon: Word-level typography control in scene text rendering","author":"Shi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Measuring style similarity in diffusion models","author":"Somepalli","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Processpainter: Learn painting process from sequence data","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Anti-reference: Universal and immediate defense against reference-based generation","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01835"},{"key":"ref65","article-title":"Makeanything: Harnessing diffusion transformers for multidomain procedural sequence generation","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Omniconsistency: Learning style-agnostic consistency from paired stylization data","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00287"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref69","article-title":"Hugging Face Team","year":"2023","journal-title":"Stable diffusion reference implementation"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref71","article-title":"Grid: Visual layout generation","author":"Wan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00661"},{"key":"ref75","article-title":"Diffdecompose: Layer-wise decomposition of alpha-composited images via diffusion transformers","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1804"},{"key":"ref79","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"A general protocol to probe large vision models for 3d physical understanding","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhan","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref84","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"arXiv preprint","author":"Zhang","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447042"},{"key":"ref87","article-title":"Stablemakeup: When real-world makeup transfer meets diffusion model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33123"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01814"}],"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\/11444970.pdf?arnumber=11444970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:01Z","timestamp":1777611661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01570","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}