{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T06:08:53Z","timestamp":1789106933502,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032377173","type":"print"},{"value":"9783032377180","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\/978-3-032-37718-0_29","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:52:49Z","timestamp":1789105969000},"page":"510-525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AC3S: Adaptive Conditioning for\u00a03D-Aware Synthetic Data Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1811-2930","authenticated-orcid":false,"given":"Eric","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1753-0189","authenticated-orcid":false,"given":"Qiran","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4696-2833","authenticated-orcid":false,"given":"Wufei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarthak","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1858-4257","authenticated-orcid":false,"given":"Yingying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5132-4986","authenticated-orcid":false,"given":"Minh N.","family":"Do","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5316-3028","authenticated-orcid":false,"given":"Yaoyao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"29_CR1","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification (2023). arXiv preprint arXiv:2304.08466"},{"key":"29_CR2","unstructured":"Bordes, F., et\u00a0al.: An introduction to vision-language modeling. arXiv preprint arXiv:2405.17247 (2024)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Canny, J.: A computational approach to edge detection. TPAMI, pp. 679\u2013698 (2009)","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"29_CR4","unstructured":"Cao, W., et al.: Redirect4d-bench: a scalable benchmark for camera redirection of monocular dynamic videos with pseudo-4d ground truth (2026)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Cao, W., et al.: FreeOrbit4D: training-free arbitrary camera redirection for monocular videos via foreground-complete 4D reconstruction. In: SIGGRAPH (2026)","DOI":"10.1145\/3799902.3811122"},{"key":"29_CR6","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3d model repository (2015). arXiv preprint arXiv:1512.03012"},{"key":"29_CR7","unstructured":"Community, B.O.: Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam (2018)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: CVPR, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR10","unstructured":"Duan, R., Chen, J., Kortylewski, A., Yuille, A., Liu, Y.: Prompt-based exemplar super-compression and regeneration for class-incremental learning. In: BMVC (2025)"},{"key":"29_CR11","doi-asserted-by":"publisher","unstructured":"Fischer, T., et al.: iNeMo: incremental neural mesh models for robust class-incremental learning. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15135, pp. 357\u2013374 . Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72980-5_21","DOI":"10.1007\/978-3-031-72980-5_21"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Fu, S., et al.: Dreamsim: learning new dimensions of human visual similarity using synthetic data (2023). arXiv preprint arXiv:2306.09344","DOI":"10.52202\/075280-2208"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR14","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? (2022). arXiv preprint arXiv:2210.07574"},{"key":"29_CR15","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. NeurIPS (2017)"},{"key":"29_CR16","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS, pp. 6840\u20136851 (2020)"},{"key":"29_CR17","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020)"},{"key":"29_CR18","unstructured":"Hong, S., et al.: Metagpt: meta programming for a multi-agent collaborative framework. In: The Twelfth ICLR (2023)"},{"key":"29_CR19","unstructured":"Li, Y., Chen, X., Li, N.: Online optimal control with linear dynamics and predictions: algorithms and regret analysis. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Das, S., Li, N.: Online optimal control with affine constraints. In: AAAI, pp. 8527\u20138537 (2021)","DOI":"10.1609\/aaai.v35i10.17035"},{"issue":"10","key":"29_CR21","doi-asserted-by":"publisher","first-page":"4761","DOI":"10.1109\/TAC.2020.3040249","volume":"66","author":"Y Li","year":"2020","unstructured":"Li, Y., Qu, G., Li, N.: Online optimization with predictions and switching costs: fast algorithms and the fundamental limit. IEEE Trans. Autom. Control 66(10), 4761\u20134768 (2020)","journal-title":"IEEE Trans. Autom. Control"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Q., et al.: Tasr: timestep-aware diffusion model for image super-resolution. In: ACM Multimedia, pp. 10034\u201310043 (2025)","DOI":"10.1145\/3746027.3755335"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., Schiele, B., Sun, Q.: Online hyperparameter optimization for class-incremental learning. In: AAAI, pp. 8906\u20138913 (2023)","DOI":"10.1609\/aaai.v37i7.26070"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., Schiele, B., Sun, Q.: Wakening past concepts without past data: class-incremental learning from online placebos. In: WACV, pp. 2226\u20132235 (2024)","DOI":"10.1109\/WACV57701.2024.00222"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Schiele, B., Sun, Q.: Adaptive aggregation networks for class-incremental learning. In: CVPR, pp. 2544\u20132553 (2021)","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"29_CR26","first-page":"3478","volume":"34","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Schiele, B., Sun, Q.: RMM: reinforced memory management for class-incremental learning. NeurIPS 34, 3478\u20133490 (2021)","journal-title":"NeurIPS"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Schiele, B., Vedaldi, A., Rupprecht, C.: Continual detection transformer for incremental object detection. In: CVPR, pp. 23799\u201323808 (2023)","DOI":"10.1109\/CVPR52729.2023.02279"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Su, Y., Liu, A.A., Schiele, B., Sun, Q.: Mnemonics training: multi-class incremental learning without forgetting. In: CVPR, pp. 12245\u201312254 (2020)","DOI":"10.1109\/CVPR42600.2020.01226"},{"issue":"6","key":"29_CR29","first-page":"2733","volume":"32","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, Q., He, X., Liu, A., Su, Y., Chua, T.: Generating face images with attributes for free. TNNLS 32(6), 2733\u20132743 (2021)","journal-title":"TNNLS"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Luo, Z., Liu, Y., Schiele, B., Sun, Q.: Class-incremental exemplar compression for class-incremental learning. In: CVPR, pp. 11371\u201311380 (2023)","DOI":"10.1109\/CVPR52729.2023.01094"},{"key":"29_CR33","unstructured":"Ma, W., et al.: Generating images with 3d annotations using diffusion models. In: ICLR (2023)"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: Imagenet3d: towards general-purpose object-level 3d understanding. In: NeurIPS (2024)","DOI":"10.52202\/079017-3046"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Nguyen, Q., Vu, T., Tran, A., Nguyen, K.: Dataset diffusion: diffusion-based synthetic data generation for pixel-level semantic segmentation. NeurIPS, pp. 76872\u201376892 (2023)","DOI":"10.52202\/075280-3359"},{"key":"29_CR36","unstructured":"OpenAI: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR37","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: NeurIPS 2017 Autodiff Workshop (2017)"},{"key":"29_CR38","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis (2023). arXiv preprint arXiv:2307.01952"},{"key":"29_CR39","unstructured":"Robino, G.: Conversation routines: a prompt engineering framework for task-oriented dialog systems (2025). arXiv preprint arXiv:2501.11613"},{"key":"29_CR40","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI, pp, 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, pp. 36479\u201336494 (2022)","DOI":"10.52202\/068431-2643"},{"key":"29_CR43","unstructured":"Singer, U., et al.: Make-a-video: text-to-video generation without text-video data. In: ICLR (2023)"},{"key":"29_CR44","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"29_CR45","unstructured":"Team, Q.: Qwen technical report (2023). arXiv preprint arXiv:2309.16609"},{"key":"29_CR46","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models (2023). arXiv preprint arXiv:2302.07944"},{"key":"29_CR47","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: ICLR (2023)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. NeurIPS, pp. 24824\u201324837 (2022)","DOI":"10.52202\/068431-1800"},{"key":"29_CR49","unstructured":"White, J., et al.: A prompt pattern catalog to enhance prompt engineering with chatgpt (2023). arXiv preprint arXiv:2302.11382"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Omniobject3d: large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. In: CVPR, pp. 803\u2013814 (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3d object detection in the wild. In: WACV, pp. 75\u201382. IEEE (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"29_CR52","doi-asserted-by":"crossref","unstructured":"Yehezkel, S., Dahary, O., Voynov, A., Cohen-Or, D.: Navigating with annealing guidance scale in diffusion space. In: SIGGRAPH Asia, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763830"},{"key":"29_CR53","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Just noticeable differences in visual attributes. In: ICCV, pp. 2416\u20132424 (2015)","DOI":"10.1109\/ICCV.2015.278"},{"key":"29_CR54","doi-asserted-by":"publisher","unstructured":"Zhang, J.O., Sax, A., Zamir, A., Guibas, L., Malik, J.: Side-tuning: a baseline for network adaptation via additive side networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12348, pp. 698\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_41","DOI":"10.1007\/978-3-030-58580-8_41"},{"issue":"8","key":"29_CR55","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. TPAMI 46(8), 5625\u20135644 (2024)","journal-title":"TPAMI"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, X., Chen, H., Yuille, A.L., Liu, Y., Zhou, Z.: Continual learning for abdominal multi-organ and tumor segmentation. In: MICCAI, pp. 35\u201345 (2023)","DOI":"10.1007\/978-3-031-43895-0_4"},{"issue":"9","key":"29_CR58","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV 130(9), 2337\u20132348 (2022)","journal-title":"IJCV"},{"key":"29_CR59","unstructured":"Zhu, D., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. In: ICLR, vol. 2024, 18378\u201318394 (2024)"},{"key":"29_CR60","unstructured":"Zhu, Z., Gong, Y., Xiao, Y., Liu, Y., Hoiem, D.: How to teach large multimodal models new skills? In: ECCV (2026)"}],"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\/978-3-032-37718-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:53:01Z","timestamp":1789105981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37718-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032377173","9783032377180"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37718-0_29","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"}}]}}