{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:05:37Z","timestamp":1784901937970,"version":"3.55.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032314406","type":"print"},{"value":"9783032314413","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T00:00:00Z","timestamp":1784937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T00:00:00Z","timestamp":1784937600000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31441-3_27","type":"book-chapter","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T13:21:55Z","timestamp":1784899315000},"page":"401-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SCPainter: A Unified Framework for\u00a0Realistic 3D Asset Insertion and\u00a0Novel View Synthesis"],"prefix":"10.1007","author":[{"given":"Paul","family":"Dobre","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jackson","family":"Cooper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,25]]},"reference":[{"key":"27_CR1","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"issue":"12","key":"27_CR2","doi-asserted-by":"publisher","first-page":"10164","DOI":"10.1109\/TPAMI.2024.3435937","volume":"46","author":"L Chen","year":"2024","unstructured":"Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. IEEE Trans. Patt. Anal. Mach. Intell. 46(12), 10164\u201310183 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3435937","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Video depth anything: consistent depth estimation for super-long videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22831\u201322840 (2025)","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"27_CR4","unstructured":"Chen, Z., et al.: OmniRe: omni urban scene reconstruction. In: Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) (2025)"},{"key":"27_CR5","unstructured":"Chen, Y., Gu, C., Jiang, J., Zhu, X., Zhang, L.: Periodic vibration gaussian: dynamic urban scene reconstruction and real-time rendering. arXiv preprint arXiv:2311.18561 (2023)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Fan, L., Zhang, H., Wang, Q., Li, H., Zhang, Z.: FreeSim: toward free-viewpoint camera simulation in driving scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12004\u201312014 (2025)","DOI":"10.1109\/CVPR52734.2025.01121"},{"key":"27_CR7","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. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 30 (2017)"},{"issue":"4","key":"27_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (TOG) 42(4), 1\u201314 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"27_CR9","unstructured":"Lin, C., Zhuang, B., Sun, S., Jiang, Z., Cai, J., Chandraker, M.: Drive-1-to-3: enriching diffusion priors for novel view synthesis of real vehicles. arXiv preprint arXiv:2412.14494 (2024)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: DriveEditor: s unified 3D information-guided framework for controllable object editing in driving scenes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 5, pp. 5164\u20135172 (2025)","DOI":"10.1609\/aaai.v39i5.32548"},{"key":"27_CR11","unstructured":"Ljungbergh, W., Taveira, B., Zheng, W., Tonderski, A., Peng, C., Kahl, F., et al.: R3D2: realistic 3D asset insertion via diffusion for autonomous driving simulation. arXiv preprint arXiv:2506.07826 (2025)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 38\u201355. Springer Nature, Cham, Switzerland (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: ProtoCar: learning 3D vehicle prototypes from single-view and unconstrained driving scene images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 5, pp. 5460\u20135468 (2025)","DOI":"10.1609\/aaai.v39i5.32581"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Ni, C., et al..: ReconDreamer: crafting world models for driving scene reconstruction via online restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1559\u20131569 (2025)","DOI":"10.1109\/CVPR52734.2025.00153"},{"key":"27_CR15","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Ren, X., et al.: Gen3C: 3D-informed world-consistent video generation with precise camera control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6121\u20136132 (2025)","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"27_CR17","unstructured":"Singh, B., Kulharia, V., Yang, L., Ravichandran, A., Tyagi, A., Shrivastava, A.: GenMM: geometrically and temporally consistent multimodal data generation for video and LiDAR. arXiv preprint arXiv:2406.10722 (2024)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"27_CR19","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"27_CR20","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR21","unstructured":"Wang, Q., Fan, L., Wang, Y., Chen, Y., Zhang, Z.: FreeVS: generative view synthesis on free driving trajectory. In: Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) (2025)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"issue":"4","key":"27_CR23","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.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Wu, T., Zheng, C., Guan, F., Vedaldi, A., Cham, T.J.: Amodal3R: amodal 3D reconstruction from occluded 2D images. arXiv preprint arXiv:2503.13439 (2025)","DOI":"10.1109\/ICCV51701.2025.00858"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Xiang, J., Lv, Z., Xu, S., Deng, Y., Wang, R., Zhang, B., et al.: Structured 3D latents for scalable and versatile 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21469\u201321480 (2025)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Yan, Y., et al.: StreetCrafter: street view synthesis with controllable video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 822\u2013832 (2025)","DOI":"10.1109\/CVPR52734.2025.00085"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Yan, Y., et al.: Street gaussians: modeling dynamic urban scenes with gaussian splatting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 156\u2013173. Springer Nature, Cham, Switzerland (2024)","DOI":"10.1007\/978-3-031-73464-9_10"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"27_CR29","unstructured":"Yang, L., et al.: Depth Anything V2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Zhang, H., Manivasagam, S., Chen, Y., Urtasun, R.: GenAssets: generating in-the-wild 3D assets in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22392\u201322403 (2025)","DOI":"10.1109\/CVPR52734.2025.02086"},{"key":"27_CR31","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, X., Lin, Z., Shan, X., Wang, Y., Sun, D., Yang, M.H.: DrivingGaussian: composite gaussian splatting for surrounding dynamic autonomous driving scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21634\u201321643 (2024)","DOI":"10.1109\/CVPR52733.2024.02044"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31441-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T13:22:09Z","timestamp":1784899329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31441-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,25]]},"ISBN":["9783032314406","9783032314413"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31441-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,25]]},"assertion":[{"value":"25 July 2026","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":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}