{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:14:42Z","timestamp":1767323682255,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557363","type":"print"},{"value":"9789819557370","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\/978-981-95-5737-0_8","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:11:06Z","timestamp":1767323466000},"page":"105-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sync5D: Novel View Synthesis from\u00a0a\u00a0Single Image with\u00a05D Consistency"],"prefix":"10.1007","author":[{"given":"Junlin","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangkai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinggong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongming","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"8_CR1","unstructured":"Armandpour, M., Sadeghian, A., Zheng, H., 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":"8_CR2","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Generative novel view synthesis with 3D-aware diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4217\u20134229 (2023)","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Cascade-Zero123: one image to highly consistent 3D with self-prompted nearby views. arXiv preprint arXiv:2312.04424 (2023)","DOI":"10.1007\/978-3-031-72940-9_18"},{"key":"8_CR4","unstructured":"Chen, Y., Xu, H., Wu, Q., Zheng, C., Cham, T.J., Cai, J.: Explicit correspondence matching for generalizable neural radiance fields. arXiv preprint arXiv:2304.12294 (2023)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Wang, Y., Liu, H.: Text-to-3D using gaussian splatting (2024). https:\/\/arxiv.org\/abs\/2309.16585","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Deng, C., et\u00a0al.: NeRDi: single-view NeRF synthesis with language-guided diffusion as general image priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20637\u201320647 (2023)","DOI":"10.1109\/CVPR52729.2023.01977"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3D scanned household items. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2553\u20132560. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Erko\u00e7, Z., Ma, F., Shan, Q., Nie\u00dfner, M., Dai, A.: HyperDiffusion: generating implicit neural fields with weight-space diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14300\u201314310 (2023)","DOI":"10.1109\/ICCV51070.2023.01315"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Gao, Q., Zhai, S., Chen, B., Liu, L., Susskind, J.: Learning controllable 3D diffusion models from single-view images. arXiv preprint arXiv:2304.06700 (2023)","DOI":"10.1109\/3DV62453.2024.00030"},{"key":"8_CR10","unstructured":"Gu, J., et al.: NerfDiff: single-image view synthesis with NeRF-guided distillation from 3D-aware diffusion. In: International Conference on Machine Learning, pp. 11808\u201311826. PMLR (2023)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Han, J., Kokkinos, F., Torr, P.: VFusion3D: learning scalable 3D generative models from video diffusion models. arXiv preprint arXiv:2403.12034 (2024)","DOI":"10.1007\/978-3-031-72627-9_19"},{"key":"8_CR12","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020). https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"8_CR13","unstructured":"Huang, Z., Hu, K., Wang, X.: M2-Net: multi-stages specular highlight detection and removal in multi-scenes. arXiv preprint arXiv:2207.09965 (2022)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Lee, J., Kim, C., Cho, M., Lee, D.: NVS-adapter: plug-and-play novel view synthesis from a single image. arXiv preprint arXiv:2312.07315 (2023)","DOI":"10.1007\/978-3-031-73195-2_26"},{"key":"8_CR15","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Vedaldi, A., Novotny, D., Mitra, N.J.: HoloDiffusion: training a 3D diffusion model using 2D images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 18423\u201318433 (2023)","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (SIGGRAPH Conference Proceedings) 42(4) (2023). http:\/\/www-sop.inria.fr\/reves\/Basilic\/2023\/KKLD23","DOI":"10.1145\/3592433"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kim, S.W., et al.: NeuralField-LDM: scene generation with hierarchical latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8496\u20138506 (2023)","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: One-2-3-45++: fast single image to 3D objects with consistent multi-view generation and 3D diffusion. arXiv preprint arXiv:2311.07885 (2023)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"8_CR20","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization (2023). https:\/\/arxiv.org\/abs\/2306.16928"},{"key":"8_CR21","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":"8_CR22","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"8_CR23","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"},{"issue":"1","key":"8_CR24","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":"8_CR25","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bulo, S.R., Kontschieder, P., Nie\u00dfner, M.: DiffRF: rendering-guided 3D radiance field diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4328\u20134338 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"issue":"4","key":"8_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (TOG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR27","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"8_CR28","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":"8_CR29","first-page":"67021","volume":"36","author":"E Ntavelis","year":"2023","unstructured":"Ntavelis, E., Siarohin, A., Olszewski, K., Wang, C., Gool, L.V., Tulyakov, S.: AutoDecoding latent 3D diffusion models. Adv. Neural. Inf. Process. Syst. 36, 67021\u201367047 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR30","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"8_CR31","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"8_CR32","unstructured":"Qian, G., et al.: Magic123: one image to high-quality 3d object generation using both 2D and 3D diffusion priors (2023). https:\/\/arxiv.org\/abs\/2306.17843"},{"key":"8_CR33","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":"8_CR34","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)"},{"key":"8_CR35","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"8_CR36","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"8_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Tang, J., Wang, T., Zhang, B., Zhang, T., Yi, R., Ma, L., Chen, D.: Make-it-3D: high-fidelity 3D creation from a single image with diffusion prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22819\u201322829 (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"8_CR39","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Furukawa, Y.: MVDiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. arXiv preprint arXiv:2307.01097 (2023)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"issue":"4","key":"8_CR41","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR42","unstructured":"Watson, D., Chan, W., Martin-Brualla, R., Ho, J., Tagliasacchi, A., Norouzi, M.: Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628 (2022)"},{"key":"8_CR43","unstructured":"Xiong, Y., Ma, H., Sun, S., Han, K., Xie, X.: Light field diffusion for single-view novel view synthesis. arXiv preprint arXiv:2309.11525 (2023)"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Yang, J., Cheng, Z., Duan, Y., Ji, P., Li, H.: ConsistNet: enforcing 3D consistency for multi-view images diffusion. arXiv preprint arXiv:2310.10343 (2023)","DOI":"10.1109\/CVPR52733.2024.00676"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Ye, J., Wang, P., Li, K., Shi, Y., Wang, H.: Consistent-1-to-3: consistent image to 3D view synthesis via geometry-aware diffusion models. arXiv preprint arXiv:2310.03020 (2023)","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023). https:\/\/arxiv.org\/abs\/2302.05543","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"8_CR47","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, C., Vedaldi, A.: Free3D: consistent novel view synthesis without 3D representation. arXiv preprint arXiv:2312.04551 (2023)","DOI":"10.1109\/CVPR52733.2024.00928"},{"key":"8_CR49","unstructured":"Zhu, J., Zhuang, P.: HiFA: high-fidelity text-to-3D with advanced diffusion guidance. arXiv preprint arXiv:2305.18766 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5737-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:11:10Z","timestamp":1767323470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5737-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557363","9789819557370"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5737-0_8","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}