{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:40:41Z","timestamp":1742924441320,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031736674"},{"type":"electronic","value":"9783031736681"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73668-1_23","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:03:39Z","timestamp":1733018619000},"page":"391-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Label-Free Neural Semantic Image Synthesis"],"prefix":"10.1007","author":[{"given":"Jiayi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin Alexander","family":"Laube","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan Hendrik","family":"Metzen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shin-I","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julio","family":"Borges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Khoreva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"23_CR1","unstructured":"Midjourney (2023). https:\/\/www.midjourney.com\/"},{"key":"23_CR2","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep vit features as dense visual descriptors. arXiv preprint arXiv:2112.05814 (2021)"},{"key":"23_CR3","unstructured":"Balaji, Y., et\u00a0al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. TPAMI 8, 679\u2013698 (1986)","journal-title":"TPAMI"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"23_CR10","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NeurIPS (2014)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: ICCV (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR12","unstructured":"Hedlin, E., et al.: Unsupervised semantic correspondence using stable diffusion. arXiv preprint arXiv:2305.15581 (2023)"},{"key":"23_CR13","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: TIFA: accurate and interpretable text-to-image faithfulness evaluation with question answering. arXiv preprint arXiv:2303.11897 (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"23_CR16","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Pnp inversion: boosting diffusion-based editing with 3 lines of code. In: ICLR (2024)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"23_CR18","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"23_CR20","unstructured":"Li, Y., Keuper, M., Zhang, D., Khoreva, A.: Adversarial supervision makes layout-to-image diffusion models thrive. In: ICLR (2024)"},{"issue":"209","key":"23_CR21","first-page":"1","volume":"24","author":"B Lin","year":"2023","unstructured":"Lin, B., Zhang, Y.: LibMTL: a python library for multi-task learning. J. Mach. Learn. Res. 24(209), 1\u20137 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"23_CR23","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Qin, C., et al.: Gluegen: plug and play multi-modal encoders for x-to-image generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02110"},{"key":"23_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"23_CR27","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"23_CR28","doi-asserted-by":"crossref","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 (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"23_CR29","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":"23_CR30","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Van\u00a0Gool, L.: Acdc: the adverse conditions dataset with correspondences for semantic driving scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: ECCV, pp. 746\u2013760 (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"23_CR33","doi-asserted-by":"publisher","first-page":"2903","DOI":"10.1007\/s11263-022-01673-x","volume":"130","author":"V Sushko","year":"2022","unstructured":"Sushko, V., Sch\u00f6nfeld, E., Zhang, D., Gall, J., Schiele, B., Khoreva, A.: Oasis: only adversarial supervision for semantic image synthesis. IJCV 130, 2903\u20132923 (2022)","journal-title":"IJCV"},{"key":"23_CR34","first-page":"4852","volume":"44","author":"Z Tan","year":"2021","unstructured":"Tan, Z., et al.: Efficient semantic image synthesis via class-adaptive normalization. TPAMI 44, 4852\u20134866 (2021)","journal-title":"TPAMI"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"23_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"23_CR37","unstructured":"Wang, T., et al.: Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952 (2022)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional gans. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, L., Chen, Y.C., Zhang, X., Jia, J.: Image synthesis via semantic composition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"23_CR40","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. In: NeurIPS (2021)"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"23_CR42","unstructured":"Xu, S., Huang, Y., Pan, J., Ma, Z., Chai, J.: Inversion-free image editing with natural language. In: CVPR (2024)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"23_CR44","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"23_CR46","unstructured":"Zhang, J., et al.: A tale of two features: stable diffusion complements dino for zero-shot semantic correspondence. In: NeurIPS (2023)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"23_CR49","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. In: NeurIPS (2023)"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"23_CR52","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"ECCV 2022","author":"C Zhou","year":"2022","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, pp. 696\u2013712. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40"},{"key":"23_CR53","unstructured":"Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: NeurIPS (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73668-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:12:42Z","timestamp":1733019162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}