{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:05:17Z","timestamp":1782536717917,"version":"3.54.5"},"reference-count":44,"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\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["SRG2022-00023-IOTSC"],"award-info":[{"award-number":["SRG2022-00023-IOTSC"]}],"id":[{"id":"10.13039\/501100004733","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\/iccv51701.2025.01772","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Hongji","family":"Yang","sequence":"first","affiliation":[{"name":"SKL-IOTSC, CIS, University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wencheng","family":"Han","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS, University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS, University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS, University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","volume":"36","author":"Li","year":"2024","journal-title":"Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref10","volume-title":"Xinsir. Controlnetplus","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01300-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4094"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref15","article-title":"Labs","volume-title":"Flux: Official inference repository for flux. 1 models","author":"Forest","year":"2024"},{"key":"ref16","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","first-page":"129","article-title":"Controlnet ++: Improving conditional controls with efficient consistency feedback","volume-title":"European Conference on Computer Vision","author":"Li","year":"2025"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref20","article-title":"Denoising diffusion implicit models","volume-title":"arXiv preprint","author":"Song","year":"2020"},{"key":"ref21","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"arXiv preprint","author":"Liu","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref23","article-title":"Auto-encoding variational bayes","volume-title":"arXiv preprint","author":"Kingma","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref25","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref28","article-title":"Pixart- \u03b4: Fast and controllable image generation with latent consistency models","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref29","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"arXiv preprint","author":"Nichol","year":"2021"},{"key":"ref30","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref31","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","volume-title":"arXiv preprint","author":"Ye","year":"2023"},{"key":"ref32","article-title":"Wong","volume-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models. Neural Information Processing Systems","author":"Zhao","year":"2023"},{"key":"ref33","first-page":"4296142992","article-title":"Unicontrol: a unified diffusion model for controllable visual generation in the wild","volume-title":"Neural Information Processing Systems","author":"Qin","year":"2023"},{"key":"ref34","article-title":"Controlnext: Powerful and efficient control for image and video generation","volume-title":"arXiv preprint","author":"Peng","year":"2024"},{"key":"ref35","article-title":"Learning to generate images of outdoor scenes from attributes and semantic layouts","volume-title":"arXiv preprint","author":"Karacan","year":"2016"},{"key":"ref36","article-title":"Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, and Honglak Lee","volume":"29","author":"Scott","year":"2016","journal-title":"Learning what and where to draw. Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00763"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"ref40","article-title":"Geodiffusion: Textprompted geometric control for object detection data generation","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref42","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv preprint","author":"Devlin","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref44","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","volume-title":"arXiv preprint","author":"Tan","year":"2024"}],"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\/11444719.pdf?arnumber=11444719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:38Z","timestamp":1777613078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01772","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}