{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T05:40:10Z","timestamp":1746769210228,"version":"3.40.5"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031876622","type":"print"},{"value":"9783031876639","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-87663-9_16","type":"book-chapter","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T05:12:58Z","timestamp":1746767578000},"page":"187-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Addressing Janus Issue in\u00a0Text-to-3D via\u00a0Orientation-Controlled Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6705-8694","authenticated-orcid":false,"given":"Yuzhong","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0247-4328","authenticated-orcid":false,"given":"Fred","family":"Morstatter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,10]]},"reference":[{"key":"16_CR1","unstructured":"Threestudio project. https:\/\/github.com\/threestudio-project\/threestudio. Accessed 17 Nov 2023"},{"key":"16_CR2","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 preprint arXiv:2304.04968 (2023)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Bai, H., Kang, D., Zhang, H., Pan, J., Bao, L.: FFHQ-UV: normalized facial UV-texture dataset for 3D face reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 362\u2013371 (2023)","DOI":"10.1109\/CVPR52729.2023.00043"},{"key":"16_CR4","unstructured":"Balaji, Y., et\u00a0al.: eDiffI: text-to-image diffusion models with an ensemble of expert denoisers. arXiv:2211.01324 (2022)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3D generative adversarial networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN V2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"16_CR7","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (2020)"},{"key":"16_CR8","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv:2207.12598 (2022)"},{"key":"16_CR9","unstructured":"Hong, S., Ahn, D., Kim, S.: Debiasing scores and prompts of 2D diffusion for view-consistent text-to-3D generation (2023)"},{"key":"16_CR10","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 (2023)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. arXiv:2211.10440 (2022)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"16_CR12","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. arXiv:2303.11328 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"16_CR13","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image (2023)"},{"key":"16_CR14","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"16_CR15","doi-asserted-by":"crossref","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 (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. arXiv:2201.05989 (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"16_CR17","unstructured":"Ouyang, Y., Chai, W., Ye, J., Tao, D., Zhan, Y., Wang, G.: Chasing consistency in text-to-3D generation from a single image (2023)"},{"key":"16_CR18","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv:2209.14988 (2022)"},{"key":"16_CR19","unstructured":"Qian, G., et al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors (2023)"},{"key":"16_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"16_CR21","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR (2020)"},{"key":"16_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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR23","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv:2205.11487 (2022)"},{"key":"16_CR24","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation (2023)"},{"key":"16_CR25","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. arXiv:2209.14792 (2022)"},{"key":"16_CR26","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502, October 2020. https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"16_CR27","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv:2011.13456 (2020)"},{"key":"16_CR28","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. arXiv:2104.09864 (2021)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Variable bitrate neural fields. In: ACM SIGGRAPH 2022 Conference Proceedings (2022)","DOI":"10.1145\/3528233.3530727"},{"key":"16_CR30","unstructured":"Tang, J.: Stable-DreamFusion: text-to-3D with stable-diffusion (2022). github.com\/ashawkey\/stable-dreamfusion"},{"key":"16_CR31","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. arXiv:2212.00774 (2022)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"16_CR32","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. arXiv:2305.16213 (2023)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Dream3D: zero-shot text-to-3D synthesis using 3D shape prior and text-to-image diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: MVImgNet: a large-scale dataset of multi-view images. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"16_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87663-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T05:13:24Z","timestamp":1746767604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87663-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031876622","9783031876639"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87663-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"10 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}