{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:31:55Z","timestamp":1761388315168,"version":"build-2065373602"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Taishan Scholar Project of Shandong Province, China","award":["No. ts20190924","No. ts20190924","No. ts20190924"],"award-info":[{"award-number":["No. ts20190924","No. ts20190924","No. ts20190924"]}]},{"name":"the National Natural Sci- ence Foundation of China","award":["Nos. 62176144","Nos. 62176144","Nos. 62176144"],"award-info":[{"award-number":["Nos. 62176144","Nos. 62176144","Nos. 62176144"]}]},{"name":"the major fundamental research project of Shandong, China","award":["Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08","Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08","Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08"],"award-info":[{"award-number":["Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08","Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08","Nos. ZR2019ZD03, ZR2024MF043, ZR2024ZD08"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00530-025-01966-4","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:31:45Z","timestamp":1755779505000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature loop consistency optimization for enhanced control precision in text-to-image generation"],"prefix":"10.1007","volume":"31","author":[{"given":"Fucheng","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqiang","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"1966_CR1","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"6","author":"J Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679\u2013698 (1986)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1966_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Z., et al.: \u201cRealtime multi-person 2d pose estimation using part affinity fields\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"issue":"9","key":"1966_CR3","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"F-A Croitoru","year":"2023","unstructured":"Croitoru, F.-A., et al.: Diffusion models in vision: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10850\u201310869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"1966_CR4","first-page":"726","volume":"36","author":"G Geonmo","year":"2022","unstructured":"Geonmo, G., et al.: Towards light-weight and real-time line segment detection. Proceed. AAAI Conf. Artif. Intell. 36(1), 726\u2013734 (2022)","journal-title":"Proceed. AAAI Conf. Artif. Intell."},{"key":"1966_CR5","unstructured":"Hardt, M., Recht, B., Singer, Y.: \u201cTrain faster, generalize better: Stability of stochastic gradient descent\u201d. In: International conference on machine learning. PMLR. pp. 1225\u20131234 (2016)"},{"key":"1966_CR6","unstructured":"Heusel, M., et al.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"1966_CR7","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1966_CR8","unstructured":"Ho, J., Salimans, T.: \u201cClassifier-free diffusion guidance\u201d (2022). arXiv preprint arXiv:2207.12598"},{"key":"1966_CR9","unstructured":"Kingma, D.P.: \u201cAdam: A method for stochastic optimization\u201d (2014). arXiv preprint arXiv:1412.6980"},{"key":"1966_CR10","unstructured":"Kingma, D.P.: \u201cAuto-encoding variational bayes\u201d (2013). arXiv preprint arXiv:1312.6114"},{"key":"1966_CR11","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: \u201cControlNet++: Improving Conditional Controls with Efficient Consistency Feedback: Project Page: liming-ai. github. io\/ControlNet_Plus_Plus\u201d. In: European Conference on Computer Vision. Springer. pp. 129\u2013147 (2024)","DOI":"10.1007\/978-3-031-72667-5_8"},{"issue":"5","key":"1966_CR12","doi-asserted-by":"publisher","first-page":"4296","DOI":"10.1609\/aaai.v38i5.28226","volume":"38","author":"C Mou","year":"2024","unstructured":"Mou, C., et al.: T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. Proceedings of the AAAI Conference on Artificial Intelligence. 38(5), 4296\u20134304 (2024)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"1966_CR13","unstructured":"Qin, C., et al.: \u201cUnicontrol: A unified diffusion model for controllable visual generation in the wild\u201d (2023). arXiv preprint arXiv:2305.11147"},{"key":"1966_CR14","unstructured":"Radford, A., et al.: \u201cLearning transferable visual models from natural language supervision\u201d. In: International conference on machine learning. PMLR. pp. 8748\u20138763 (2021)"},{"key":"1966_CR15","unstructured":"Ramesh, A., et al.: \u201cHierarchical text-conditional image generation with clip latents\u201d (2022). arXiv preprint arXiv:2204.06125 1.2, p. 3"},{"issue":"3","key":"1966_CR16","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., et al.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1966_CR17","doi-asserted-by":"crossref","unstructured":"Rombach, R., et al.: \u201cHigh-resolution image synthesis with latent diffusion models\u201d. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1966_CR18","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: \u201cU-net: Convolutional networks for biomedical image segmentation\u201d. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer. pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"1966_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3132703","volume":"37","author":"E Simo-Serra","year":"2018","unstructured":"Simo-Serra, E., Iizuka, S., Ishikawa, H.: Mastering sketching: adversarial augmentation for structured prediction. ACM Transactions on Graphics (TOG) 37(1), 1\u201313 (2018)","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"4","key":"1966_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925972","volume":"35","author":"E Simo-Serra","year":"2016","unstructured":"Simo-Serra, E., et al.: \u201cLearning to simplify: fully convolutional networks for rough sketch cleanup\u2019\u2019. ACM Trans. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1966_CR21","unstructured":"Song, J., Meng, C., Ermon, S.: \u201cDenoising diffusion implicit models\u201d (2020). arXiv preprint arXiv:2010.02502"},{"key":"1966_CR22","doi-asserted-by":"crossref","unstructured":"Wan, Z., et al.: \u201cHigh-fidelity pluralistic image completion with transformers\u201d. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 4692\u20134701 (2021)","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"1966_CR23","doi-asserted-by":"crossref","unstructured":"Xiao, T., et al.: \u201cUnified perceptual parsing for scene understanding\u201d. In: Proceedings of the European conference on computer vision (ECCV). pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"1966_CR24","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: \u201cHolistically-nested edge detection\u201d. In: Proceedings of the IEEE international conference on computer vision. pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"1966_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, L, Rao, A., Agrawala, M.: \u201cAdding conditional control to text-to-image diffusion models\u201d. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"1966_CR26","first-page":"11127","volume":"36","author":"S Zhao","year":"2024","unstructured":"Zhao, S., et al.: Uni-controlnet: All-in-one control to text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 11127\u201311150 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01966-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01966-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01966-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:27:11Z","timestamp":1761388031000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01966-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1966"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01966-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"14 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"378"}}