{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:09:40Z","timestamp":1789124980553,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37281-9_14","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:48:43Z","timestamp":1789123723000},"page":"227-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UniGP: Taming Diffusion Transformer for\u00a0Prior-Preserved Unified Generation and\u00a0Perception"],"prefix":"10.1007","author":[{"given":"Qin","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxu","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weixuan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Bae, G., Davison, A.J.: Rethinking inductive biases for surface normal estimation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"14_CR2","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual kitti 2. arXiv preprint arXiv:2001.10773 (2020)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"14_CR4","unstructured":"Esser, P., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. arXiv preprint arXiv:2403.03206 (2024)"},{"key":"14_CR5","doi-asserted-by":"publisher","unstructured":"Fu, X., et al.: Geowizard: unleashing the diffusion priors for 3d geometry estimation from a single image. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15080, pp. 241\u2013258. Springer, Cham (2024). doi: https:\/\/doi.org\/10.1007\/978-3-031-72670-5_14","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Garcia, G.M., Zeid, K.A., Schmidt, C., de\u00a0Geus, D., Hermans, A., Leibe, B.: Fine-tuning image-conditional diffusion models is easier than you think. arXiv preprint arXiv:2409.11355 (2024)","DOI":"10.1109\/WACV61041.2025.00083"},{"key":"14_CR7","unstructured":"Github: Controlnetplus (2024). https:\/\/github.com\/xinsir6\/ControlNetPlus"},{"key":"14_CR8","unstructured":"Gui, M., et al.: DepthFM: fast monocular depth estimation with flow matching. arXiv preprint arXiv:2403.13788 (2024)"},{"key":"14_CR9","unstructured":"He, J., et al.: Lotus: diffusion-based visual foundation model for high-quality dense prediction. arXiv preprint arXiv:2409.18124 (2024)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Kar, O.F., Yeo, T., Atanov, A., Zamir, A.: 3d common corruptions and data augmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01839"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"14_CR12","unstructured":"Labs, B.F.: Flux (2024). https:\/\/blackforestlabs.ai\/announcing-black-forest-labs\/"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Le, D.H., Pham, T., Lee, S., Clark, C., Kembhavi, A., Mandt, S., Krishna, R., Lu, J.: One diffusion to generate them all. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00255"},{"key":"14_CR14","unstructured":"Li, X., Herrmann, C., Chan, K.C., Li, Y., Sun, D., Yang, M.H.: A simple approach to unifying diffusion-based conditional generation. arXiv preprint arxiv:2410.11439 (2024)"},{"key":"14_CR15","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"14_CR16","unstructured":"Midjourney: Midjourney (2024). https:\/\/www.midjourney.com"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Qin, C., et\u00a0al.: Unicontrol: a unified diffusion model for controllable visual generation in the wild. In: NeurIPS (2024)","DOI":"10.52202\/075280-1862"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"14_CR20","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. TPAMI 44(3), 1623\u20131637 (2020)","journal-title":"TPAMI"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR23","unstructured":"Stan, G.B.M., et\u00a0al.: LDM3D: latent diffusion model for 3D. arXiv preprint arXiv:2305.10853 (2023)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, Y., Tang, Y., Pei, W., Chen, K.: Anycontrol: create your artwork with versatile control on text-to-image generation. arXiv preprint arXiv:2406.18958 (2024)","DOI":"10.1007\/978-3-031-73247-8_6"},{"key":"14_CR25","unstructured":"Team, I.: Sd3-medium-controlnet (2024). https:\/\/huggingface.co\/InstantX\/SD3-Controlnet-Canny"},{"issue":"7","key":"14_CR26","first-page":"3614","volume":"44","author":"S Vandenhende","year":"2021","unstructured":"Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., Van Gool, L.: Multi-task learning for dense prediction tasks: a survey. TPAMI 44(7), 3614\u20133633 (2021)","journal-title":"TPAMI"},{"key":"14_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"14_CR28","unstructured":"Xu, G., et al.: Diffusion models trained with large data are transferable visual models. arXiv preprint arXiv:2403.06090 (2024)"},{"key":"14_CR29","unstructured":"Xu, Y., He, Z., Kan, M., Shan, S., Chen, X.: Jodi: unification of visual generation and understanding via joint modeling. arXiv preprint arXiv:2505.19084 (2025)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: Unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"14_CR31","unstructured":"Yang, L., et al.: Depth anything v2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Ye, C., et al.: Stablenormal: reducing diffusion variance for stable and sharp normal. TOG (2024)","DOI":"10.1145\/3687971"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Ye, H., Xu, D.: Diffusionmtl: learning multi-task denoising diffusion model from partially annotated data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02641"},{"key":"14_CR34","unstructured":"Zhang, J., et al.: JointNet: extending text-to-image diffusion for dense distribution modeling. In: ICLR (2024)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. In: NeurIPS (2024)","DOI":"10.52202\/075280-0491"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37281-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:48:50Z","timestamp":1789123730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}