{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:23:56Z","timestamp":1756383836410,"version":"3.40.3"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726231"},{"type":"electronic","value":"9783031726248"}],"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\/978-3-031-72624-8_19","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"324-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DreamDrone: Text-to-Image Diffusion Models Are Zero-Shot Perpetual View Generators"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5895-5112","authenticated-orcid":false,"given":"Hanyang","family":"Kong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4947-0316","authenticated-orcid":false,"given":"Dongze","family":"Lian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4930-1849","authenticated-orcid":false,"given":"Michael Bi","family":"Mi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0057-1404","authenticated-orcid":false,"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"19_CR1","first-page":"25102","volume":"35","author":"MA Bautista","year":"2022","unstructured":"Bautista, M.A., et al.: Gaudi: a neural architect for immersive 3d scene generation. Adv. Neural. Inf. Process. Syst. 35, 25102\u201325116 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Cai, S., et al.: Diffdreamer: towards consistent unsupervised single-view scene extrapolation with conditional diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2139\u20132150 (2023)","DOI":"10.1109\/ICCV51070.2023.00204"},{"key":"19_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"19_CR5","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR6","first-page":"16890","volume":"35","author":"M Ding","year":"2022","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: Cogview2: faster and better text-to-image generation via hierarchical transformers. Adv. Neural. Inf. Process. Syst. 35, 16890\u201316902 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR7","unstructured":"Fridman, R., Abecasis, A., Kasten, Y., Dekel, T.: Scenescape: text-driven consistent scene generation. arXiv preprint arXiv:2302.01133 (2023)"},{"key":"19_CR8","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: Tokenflow: consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373 (2023)"},{"key":"19_CR9","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv:2204.03458 (2022)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2room: extracting textured 3d meshes from 2d text-to-image models. arXiv preprint arXiv:2303.11989 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"19_CR11","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 867\u2013876 (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: 3d-togo: towards text-guided cross-category 3d object generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1051\u20131059 (2023)","DOI":"10.1609\/aaai.v37i1.25186"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Kong, H., Gong, K., Lian, D., Mi, M.B., Wang, X.: Priority-centric human motion generation in discrete latent space. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14806\u201314816 (2023)","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"19_CR16","unstructured":"Lee, H.H., Chang, A.X.: Understanding pure clip guidance for voxel grid nerf models. arXiv preprint arXiv:2209.15172 (2022)"},{"key":"19_CR17","unstructured":"Li, J., Bansal, M.: Panogen: text-conditioned panoramic environment generation for vision-and-language navigation. arXiv preprint arXiv:2305.19195 (2023)"},{"key":"19_CR18","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1007\/978-3-031-19769-7_30","volume-title":"European Conference on Computer Vision","author":"Z Li","year":"2022","unstructured":"Li, Z., Wang, Q., Snavely, N., Kanazawa, A.: Infinitenature-zero: learning perpetual view generation of natural scenes from single images. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13661, pp. 515\u2013534. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_30"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, A., Tucker, R., Jampani, V., Makadia, A., Snavely, N., Kanazawa, A.: Infinite nature: perpetual view generation of natural scenes from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14458\u201314467 (2021)","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"19_CR21","unstructured":"Liu, M., et\u00a0al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)"},{"key":"19_CR22","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"19_CR23","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Videofusion: decomposed diffusion models for high-quality video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10209\u201310218 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L., Laina, I., Rupprecht, C., Vedaldi, A.: Realfusion: 360deg reconstruction of any object from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8446\u20138455 (2023)","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3d shapes and textures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12663\u201312673 (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"issue":"1","key":"19_CR27","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"19_CR28","unstructured":"Mo, S., et al.: Dit-3d: exploring plain diffusion transformers for 3d shape generation. arXiv preprint arXiv:2307.01831 (2023)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Mohammad\u00a0Khalid, N., Xie, T., Belilovsky, E., Popa, T.: Clip-mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3550469.3555392"},{"key":"19_CR30","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)"},{"key":"19_CR31","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"issue":"2","key":"19_CR32","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TPAMI.2019.2934052","volume":"43","author":"J Qiu","year":"2019","unstructured":"Qiu, J., Wang, X., Fua, P., Tao, D.: Matching seqlets: an unsupervised approach for locality preserving sequence matching. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 745\u2013752 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"3","key":"19_CR34","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. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Rockwell, C., Fouhey, D.F., Johnson, J.: Pixelsynth: generating a 3d-consistent experience from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14104\u201314113 (2021)","DOI":"10.1109\/ICCV48922.2021.01384"},{"key":"19_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_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":"19_CR38","unstructured":"Shen, Q., Yang, X., Wang, X.: Anything-3d: towards single-view anything reconstruction in the wild. arXiv preprint arXiv:2304.10261 (2023)"},{"key":"19_CR39","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. arXiv preprint arXiv:2209.14792 (2022)"},{"key":"19_CR40","unstructured":"Tan, Z., Yang, X., Liu, S., Wang, X.: Video-infinity: distributed long video generation. arXiv preprint arXiv:2406.16260 (2024)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-it-3d: high-fidelity 3d creation from a single image with diffusion prior. arXiv preprint arXiv:2303.14184 (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"19_CR42","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. arXiv preprint arXiv:2306.03881 (2023)"},{"key":"19_CR43","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"19_CR44","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"19_CR45","unstructured":"Wang, W., et al.: Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599 (2023)"},{"key":"19_CR46","unstructured":"Wang, Y., et\u00a0al.: Lavie: high-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)"},{"key":"19_CR47","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"19_CR48","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Yang, C.A., et al.: Scene graph expansion for semantics-guided image outpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15617\u201315626 (2022)","DOI":"10.1109\/CVPR52688.2022.01517"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, X.: Hash3d: training-free acceleration for 3d generation. arXiv preprint arXiv:2404.06091 (2024)","DOI":"10.36227\/techrxiv.171208938.83786646\/v1"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Yu, H., Li, R., Xie, S., Qiu, J.: Shadow-enlightened image outpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7850\u20137860 (2024)","DOI":"10.1109\/CVPR52733.2024.00750"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Yu, H.X., et\u00a0al.: Wonderjourney: going from anywhere to everywhere. arXiv preprint arXiv:2312.03884 (2023)","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"19_CR53","unstructured":"Yu, T., et al.: Inpaint anything: segment anything meets image inpainting. arXiv preprint arXiv:2304.06790 (2023)"},{"key":"19_CR54","unstructured":"Zeng, X., et al.: Lion: latent point diffusion models for 3d shape generation. arXiv preprint arXiv:2210.06978 (2022)"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: Show-1: marrying pixel and latent diffusion models for text-to-video generation. arXiv preprint arXiv:2309.15818 (2023)","DOI":"10.1007\/s11263-024-02271-9"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Pointclip: point cloud understanding by clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8552\u20138562 (2022)","DOI":"10.1109\/CVPR52688.2022.00836"}],"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\/978-3-031-72624-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:47:07Z","timestamp":1732952827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72624-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726231","9783031726248"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72624-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}