{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:36:13Z","timestamp":1777570573554,"version":"3.51.4"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726972","type":"print"},{"value":"9783031726989","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72698-9_21","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T04:45:57Z","timestamp":1729831557000},"page":"358-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DreamView: Injecting View-Specific Text Guidance Into Text-to-3D Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6531-0070","authenticated-orcid":false,"given":"Junkai","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6784-6944","authenticated-orcid":false,"given":"Yipeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qize","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuansong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7969-3190","authenticated-orcid":false,"given":"Ancong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"21_CR1","unstructured":"Armandpour, M., Zheng, H., Sadeghian, A., Sadeghian, A., Zhou, M.: Re-imagine the negative prompt algorithm: Transform 2d diffusion into 3d, alleviate janus problem and beyond. arXiv (2023)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-nerf: a multiscale representation for anti-aliasing neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: High-resolution video synthesis with latent diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chang, K.H., Cheng, C.Y., Luo, J., Murata, S., Nourbakhsh, M., Tsuji, Y.: Building-gan: Graph-conditioned architectural volumetric design generation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01174"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Choi, H., et\u00a0al.: On the use of simulation in robotics: Opportunities, challenges, and suggestions for moving forward. PNAS (2021)","DOI":"10.1073\/pnas.1907856118"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Wang, Z., Zheng, W.S., Xie, C., Zhou, Y.: Sculpting holistic 3d representation in contrastive language-image-3d pre-training. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02170"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Gao, Y., Yang, L., Huang, Y., Xie, S., Li, S., Zheng, W.S.: Acrofod: an adaptive method for cross-domain few-shot object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_39"},{"key":"21_CR11","unstructured":"Ge, Y., Xu, J., Zhao, B.N., Joshi, N., Itti, L., Vineet, V.: Beyond generation: Harnessing text to image models for object detection and segmentation. arXiv (2023)"},{"key":"21_CR12","unstructured":"Ge, Y., Yu, H.X., Zhao, C., Guo, Y., Huang, X., Ren, L., Itti, L., Wu, J.: 3d copy-paste: Physically plausible object insertion for monocular 3d detection. In: NeurIPS (2024)"},{"key":"21_CR13","unstructured":"Guo, Y.C., et al.: threestudio: A unified framework for 3d content generation (2023). https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"21_CR14","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"21_CR15","unstructured":"Hong, S., Ahn, D., Kim, S.: Debiasing scores and prompts of 2d diffusion for robust text-to-3d generation. In: CVPR-W (2023)"},{"key":"21_CR16","unstructured":"Huang, Y., Wang, J., Shi, Y., Qi, X., Zha, Z.J., Zhang, L.: Dreamtime: an improved optimization strategy for text-to-3d content creation. In: ICLR (2024)"},{"key":"21_CR17","unstructured":"Jun, H., Nichol, A.: Shap-e: Generating conditional 3d implicit functions. arXiv (2023)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: Text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"21_CR19","unstructured":"Li, C., et al.: Generative ai meets 3d: A survey on text-to-3d in aigc era. arXiv (2023)"},{"key":"21_CR20","unstructured":"Li, C., et\u00a0al.: Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In: CoRL (2023)"},{"key":"21_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"21_CR22","unstructured":"Li, W., Chen, R., Chen, X., Tan, P.: Sweetdreamer: aligning geometric priors in 2d diffusion for consistent text-to-3d. In: ICLR (2024)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"21_CR24","unstructured":"Lin, K.Y., Du, J.R., Gao, Y., Zhou, J., Zheng, W.S.: Diversifying spatial-temporal perception for video domain generalization. In: NeurIPS (2024)"},{"key":"21_CR25","unstructured":"Liu, M., et al.: Openshape: Scaling up 3d shape representation towards open-world understanding. In: NeurIPS (2024)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"21_CR27","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. In: ICLR (2024)"},{"key":"21_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"21_CR31","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: A system for generating 3d point clouds from complex prompts. arXiv (2022)"},{"key":"21_CR32","unstructured":"OpenAI: Gpt-4 technical report. arXiv (2023)"},{"key":"21_CR33","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. In: ICLR (2023)"},{"key":"21_CR34","unstructured":"Qian, G., et\u00a0al.: Magic123: one image to high-quality 3d object generation using both 2d and 3d diffusion priors. In: ICLR (2024)"},{"key":"21_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"21_CR36","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":"21_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"21_CR38","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"21_CR39","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv (2021)"},{"key":"21_CR40","unstructured":"Seo, J., et al.: Let 2d diffusion model know 3d-consistency for robust text-to-3d generation. In: ICLR (2024)"},{"key":"21_CR41","unstructured":"Shao, R., et al.: Control4d: Dynamic portrait editing by learning 4d gan from 2d diffusion-based editor. arXiv (2023)"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"21_CR43","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In: NeurIPS (2021)"},{"key":"21_CR44","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3d generation. In: ICLR (2024)"},{"key":"21_CR45","unstructured":"Shi, Z., Peng, S., Xu, Y., Geiger, A., Liao, Y., Shen, Y.: Deep generative models on 3d representations: A survey. arXiv (2022)"},{"key":"21_CR46","unstructured":"Singer, U., et al.: Text-to-4d dynamic scene generation. arXiv (2023)"},{"key":"21_CR47","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Srinivasan, K., Raman, K., Chen, J., Bendersky, M., Najork, M.: Wit: wikipedia-based image text dataset for multimodal multilingual machine learning. In: ACM SIGIR (2021)","DOI":"10.1145\/3404835.3463257"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Taheri, O., Choutas, V., Black, M.J., Tzionas, D.: Goal: generating 4d whole-body motion for hand-object grasping. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"21_CR50","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Yasutaka, F.: Mvdiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. In: NeurIPS (2023)"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2d diffusion models for 3d generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"21_CR52","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: Neus: learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: NeurIPS (2021)"},{"key":"21_CR53","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. In: NeurIPS (2023)"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: Smartbrush: text and shape guided object inpainting with diffusion model. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: Ulip: learning a unified representation of language, images, and point clouds for 3d understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: Ulip-2: towards scalable multimodal pre-training for 3d understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"21_CR58","doi-asserted-by":"crossref","unstructured":"Yin, X., Wonka, P., Razdan, A.: Generating 3d building models from architectural drawings: a survey. IEEE Comput Graph (2008)","DOI":"10.1109\/MCG.2009.9"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cao, S., Wang, Y.X.: Tamm: triadapter multi-modal learning for 3d shape understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02023"},{"key":"21_CR60","unstructured":"Zhou, J., Liang, J., Lin, K.Y., Yang, J., Zheng, W.S.: Actionhub: A large-scale action video description dataset for zero-shot action recognition. arXiv (2024)"},{"key":"21_CR61","unstructured":"Zhou, J., Wang, J., Ma, B., Liu, Y.S., Huang, T., Wang, X.: Uni3d: exploring unified 3d representation at scale. In: ICLR (2024)"}],"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\/978-3-031-72698-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T04:52:10Z","timestamp":1729831930000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72698-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726972","9783031726989"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72698-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}