{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T20:14:54Z","timestamp":1783282494155,"version":"3.54.6"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017630","name":"Ministry of Education of the People's Republic of China Humanities and Social Sciences Youth Foundation","doi-asserted-by":"publisher","award":["24YJCZH146"],"award-info":[{"award-number":["24YJCZH146"]}],"id":[{"id":"10.13039\/501100017630","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104832","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:39:41Z","timestamp":1780936781000},"page":"104832","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["M-Control: Improving text\u2013image consistency via Mask-Guided ControlNet"],"prefix":"10.1016","volume":"270","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7700-4024","authenticated-orcid":false,"given":"Xinlong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2996-203X","authenticated-orcid":false,"given":"Jia","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4383-3905","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zejian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3097-5477","authenticated-orcid":false,"given":"Yongxing","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongchuan","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104832_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104223","article-title":"Unsupervised co-generation of foreground\u2013background segmentation from text-to-image synthesis","volume":"250","author":"Ahmed","year":"2025","journal-title":"Comput. Vis. Image Underst.","ISSN":"https:\/\/id.crossref.org\/issn\/1077-3142","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104832_b2","series-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b3","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2019"},{"key":"10.1016\/j.cviu.2026.104832_b4","series-title":"MasaCtrl: Tuning-free mutual self-attention control for consistent image synthesis and editing","author":"Cao","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b5","doi-asserted-by":"crossref","unstructured":"Chan, C., Durand, F., Isola, P., 2022. Learning to Generate Line Drawings that Convey Geometry and Semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7915\u20137925.","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"10.1016\/j.cviu.2026.104832_b6","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A., 2024. Training-Free Layout Control With Cross-Attention Guidance. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision. pp. 5343\u20135353.","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"10.1016\/j.cviu.2026.104832_b7","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"1691","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020"},{"key":"10.1016\/j.cviu.2026.104832_b8","series-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b9","unstructured":"Child, R., 2021. Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b10","series-title":"FluxSpace: Disentangled semantic editing in rectified flow transformers","author":"Dalva","year":"2024"},{"key":"10.1016\/j.cviu.2026.104832_b11","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104832_b12","series-title":"Diffusion self-guidance for controllable image generation","author":"Epstein","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104224","article-title":"Enhancing scene text detectors with realistic text image synthesis using diffusion models","volume":"250","author":"Fu","year":"2025","journal-title":"Comput. Vis. Image Underst.","ISSN":"https:\/\/id.crossref.org\/issn\/1077-3142","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104832_b14","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-Or, D., 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b15","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104832_b16","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., Guo, B., 2022. Vector Quantized Diffusion Model for Text-to-Image Synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10696\u201310706.","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"10.1016\/j.cviu.2026.104832_b17","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D., 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104832_b19","doi-asserted-by":"crossref","first-page":"3409","DOI":"10.1109\/TMM.2022.3160360","article-title":"TextFace: Text-to-style mapping based face generation and manipulation","volume":"25","author":"Hou","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104832_b20","series-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b21","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"key":"10.1016\/j.cviu.2026.104832_b22","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and Improving the Image Quality of StyleGAN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"10.1016\/j.cviu.2026.104832_b23","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C., 2022. DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2426\u20132435.","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"10.1016\/j.cviu.2026.104832_b24","unstructured":"Kwon, G., Ye, J.C., 2022. Diffusion-based Image Translation using Disentangled Style and Content Representation. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b25","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.-S., 2022. Autoregressive Image Generation using Residual Quantization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 11523\u201311532.","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"10.1016\/j.cviu.2026.104832_b26","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., Lee, Y.J., 2023. Gligen: Open-Set Grounded Text-to-Image Generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 22511\u201322521.","DOI":"10.1109\/CVPR52729.2023.02156"},{"issue":"12","key":"10.1016\/j.cviu.2026.104832_b27","doi-asserted-by":"crossref","first-page":"3075","DOI":"10.1109\/TMM.2020.2972856","article-title":"Exploring global and local linguistic representations for text-to-image synthesis","volume":"22","author":"Li","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104832_b28","doi-asserted-by":"crossref","unstructured":"Li, Z., Wu, J., Koh, I., Tang, Y., Sun, L., 2021. Image Synthesis From Layout With Locality-Aware Mask Adaption. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 13819\u201313828.","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"10.1016\/j.cviu.2026.104832_b29","series-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part VII","isbn-type":"print","first-page":"129","article-title":"ControlNet++: Improving conditional controls with efficient consistency feedback","author":"Li","year":"2024","ISBN":"https:\/\/id.crossref.org\/isbn\/9783031726668"},{"key":"10.1016\/j.cviu.2026.104832_b30","series-title":"Hunyuan-DiT: A powerful multi-resolution diffusion transformer with fine-grained Chinese understanding","author":"Li","year":"2024"},{"key":"10.1016\/j.cviu.2026.104832_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103259","article-title":"Diversified text-to-image generation via deep mutual information estimation","volume":"211","author":"Li","year":"2021","journal-title":"Comput. Vis. Image Underst.","ISSN":"https:\/\/id.crossref.org\/issn\/1077-3142","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104832_b32","series-title":"DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104832_b33","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D., 2023. Null-Text Inversion for Editing Real Images Using Guided Diffusion Models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6038\u20136047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"10.1016\/j.cviu.2026.104832_b34","series-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","author":"Mou","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b35","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022"},{"key":"10.1016\/j.cviu.2026.104832_b36","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.cviu.2026.104832_b37","series-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"issue":"3","key":"10.1016\/j.cviu.2026.104832_b38","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","volume":"44","author":"Ranftl","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104832_b39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B., 2022. High-Resolution Image Synthesis With Latent Diffusion Models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.cviu.2026.104832_b40","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K., 2023. Dreambooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 22500\u201322510.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"10.1016\/j.cviu.2026.104832_b41","doi-asserted-by":"crossref","first-page":"36479","DOI":"10.52202\/068431-2643","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104832_b42","unstructured":"Sheynin, S., Ashual, O., Polyak, A., Singer, U., Gafni, O., Nachmani, E., Taigman, Y., 2023. kNN-Diffusion: Image Generation via Large-Scale Retrieval. In: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b43","unstructured":"Song, J., Meng, C., Ermon, S., 2021. Denoising Diffusion Implicit Models. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104832_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104292","article-title":"DM-align: Leveraging the power of natural language instructions to make changes to images","volume":"252","author":"Trusca","year":"2025","journal-title":"Comput. Vis. Image Underst.","ISSN":"https:\/\/id.crossref.org\/issn\/1077-3142","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104832_b45","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T., 2023. Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1921\u20131930.","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"10.1016\/j.cviu.2026.104832_b46","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume":"33","author":"Vahdat","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104832_b47","doi-asserted-by":"crossref","unstructured":"Wang, L., Shen, G., Ge, W., Chen, G., Li, Y., Chen, Y., 2024. Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models. In: European Conference on Computer Vision. pp. 21\u201337.","DOI":"10.1007\/978-3-031-72970-6_2"},{"key":"10.1016\/j.cviu.2026.104832_b48","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z., 2023. BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 7452\u20137461.","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"10.1016\/j.cviu.2026.104832_b49","series-title":"Versatile diffusion: Text, images and variations all in one diffusion model","author":"Xu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104832_b50","doi-asserted-by":"crossref","first-page":"9804","DOI":"10.1109\/TMM.2024.3399075","article-title":"SGDM: An adaptive style-guided diffusion model for personalized text to image generation","volume":"26","author":"Xu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104832_b51","unstructured":"Yang, L., Yu, Z., Meng, C., Xu, M., Ermon, S., Cui, B., 2024. Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs. In: International Conference on Machine Learning."},{"issue":"8","key":"10.1016\/j.cviu.2026.104832_b52","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1109\/TMM.2019.2951463","article-title":"CKD: Cross-task knowledge distillation for text-to-image synthesis","volume":"22","author":"Yuan","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104832_b53","series-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part LXXXVIII","isbn-type":"print","first-page":"343","article-title":"ControlNet-XS: Rethinking the control of text-to-image diffusion models as feedback-control systems","author":"Zavadski","year":"2024","ISBN":"https:\/\/id.crossref.org\/isbn\/9783031732225"},{"key":"10.1016\/j.cviu.2026.104832_b54","series-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b55","series-title":"Uni-ControlNet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.cviu.2026.104832_b56","doi-asserted-by":"crossref","first-page":"6000","DOI":"10.1109\/TMM.2022.3203220","article-title":"P2-GAN: Efficient stroke style transfer using single style image","volume":"25","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Multimed."}],"updated-by":[{"DOI":"10.1016\/j.cviu.2026.104854","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000}}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001992?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001992?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T19:25:54Z","timestamp":1783279554000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"alternative-id":["S1077314226001992"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104832","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"M-Control: Improving text\u2013image consistency via Mask-Guided ControlNet","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104832","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104832"}}