{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T02:05:07Z","timestamp":1782353107668,"version":"3.54.5"},"reference-count":85,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032011"],"award-info":[{"award-number":["62032011"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01415","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15253-15265","source":"Crossref","is-referenced-by-count":2,"title":["CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Gaoyang","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingtao","family":"Fu","sequence":"additional","affiliation":[{"name":"Ant Group,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingnan","family":"Fan","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runxing","family":"Liu","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Gu","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinguo","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref2","author":"Betker","journal-title":"Improving Image Generation with Better Captions"},{"key":"ref3","article-title":"Training diffusion models with reinforcement learning","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Black"},{"key":"ref4","article-title":"FLUX.1-dev","year":"2024","journal-title":"Black Forest Labs"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888913000350"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888913000350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref11","article-title":"Pixart- $\\delta$: Fast and controllable image generation with latent consistency models","volume":"abs\/2401.05252","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref12","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Chen"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0265"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/jmla.2000.2742"},{"key":"ref17","volume-title":"Dalle mini","author":"Dayma","year":"2021"},{"key":"ref18","first-page":"87808794","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021","author":"Dhariwal"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref20","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Esser"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3497"},{"key":"ref22","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Feng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref24","article-title":"Tc-bench: Benchmarking temporal compositionality in text-to-video and image-tovideo generation","volume":"abs\/2406.08656","author":"Feng","year":"2024","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref26","article-title":"Benchmarking spatial relationships in text-to-image generation","volume":"abs\/2212.10015","author":"Gokhale","year":"2022","journal-title":"C o R R"},{"key":"ref27","article-title":"Diffusion-rpo: Aligning diffusion models through relative preference optimization","volume":"abs\/2406.06382","author":"Gu","year":"2024","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_56"},{"key":"ref29","article-title":"Ganspace: Discovering interpretable GAN controls","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"H\u00e4rk\u00f6nen"},{"key":"ref30","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Hertz"},{"key":"ref31","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Heusel"},{"key":"ref32","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Ho"},{"key":"ref33","article-title":"ELLA: equip diffusion models with LLM for enhanced semantic alignment","volume":"abs\/2403.05135","author":"Hu","year":"2024","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref38","article-title":"Scalable ranked preference optimization for text-to-image generation","volume":"abs\/2410.18013","author":"Karthik","year":"2024","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"ref40","article-title":"Photomaker: Customizing realistic human photos via stacked ID embedding","volume":"abs\/2312.04461","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref41","article-title":"Llmgrounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680658"},{"key":"ref47","year":"2023","journal-title":"Inc. MidJourney. Midjourney: Ai-powered image generation"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref49","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 2022","author":"Quinn Nichol"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref53","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Podell"},{"key":"ref54","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Poole"},{"key":"ref55","first-page":"87488763","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Radford"},{"key":"ref56","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"abs\/2204.06125","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref60","year":"2023","journal-title":"Runwayml: Creative ai tools for content creation"},{"key":"ref61","article-title":"Dual caption preference optimization for diffusion models","volume":"abs\/2502.06023","author":"Saeidi","year":"2025","journal-title":"CoRR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.723"},{"key":"ref64","article-title":"LAION400 M: open dataset of clip-filtered 400 million image-text pairs","volume":"abs\/2111.02114","author":"Schuhmann","year":"2021","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref66","article-title":"A picture is worth a thousand words: Principled recaptioning improves image generation","volume":"abs\/2310.16656","author":"Segalis","year":"2023","journal-title":"CoRR"},{"key":"ref67","article-title":"Box it to bind it: Unified layout control and attribute binding in t2i diffusion models","volume":"abs\/2402.17910","author":"Taghipour","year":"2024","journal-title":"CoRR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref70","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","volume":"abs\/2401.07519","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00817"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref74","article-title":"Paragraph-to-image generation with information-enriched diffusion model","volume":"abs\/2311.14284","author":"Wu","year":"2023","journal-title":"CoRR"},{"key":"ref75","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume-title":"CoRR","volume":"abs\/2306.09341","author":"Wu","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref79","article-title":"R&b: Region and boundary aware zero-shot grounded text-to-image generation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Xiao"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref81","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","volume":"abs\/2308.06721","author":"Ye","year":"2023","journal-title":"CoRR"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref83","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"}],"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\/11444608.pdf?arnumber=11444608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:28Z","timestamp":1777530208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01415","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}