{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:45:37Z","timestamp":1785757537971,"version":"3.56.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032313348","type":"print"},{"value":"9783032313355","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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\/978-3-032-31335-5_16","type":"book-chapter","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T10:59:19Z","timestamp":1785754759000},"page":"227-241","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LFG: Local Controllable 3D Generation Using Latent Flexible Grid Representation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7662-7999","authenticated-orcid":false,"given":"Kaiyi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1104-6883","authenticated-orcid":false,"given":"Tian","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-9437","authenticated-orcid":false,"given":"Long","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"16_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3d point clouds. In: International Conference on Machine Learning, pp. 40\u201349. PMLR (2018)"},{"key":"16_CR2","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3d model repository, arXiv preprint arXiv:1512.03012 (2015)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: 3dtopia-xl: scaling high-quality 3d asset generation via primitive diffusion, arXiv preprint arXiv:2409.12957 (2024)","DOI":"10.1109\/CVPR52734.2025.02475"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tulyakov, S., Schwing, A.G., Gui, L.Y.: Sdfusion: multimodal 3d shape completion, reconstruction, and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4456\u20134465 (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"16_CR5","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers, arXiv preprint arXiv:2309.16588 (2023)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"16_CR7","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3dgen: triplane latent diffusion for textured mesh generation, arXiv preprint arXiv:2303.05371 (2023)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance, arXiv preprint arXiv:2207.12598 (2022)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z., Boss, M., Vasishta, A., Rehg, J.M., Jampani, V.: Spar3d: stable point-aware reconstruction of 3d objects from single images. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16860\u201316870 (2025)","DOI":"10.1109\/CVPR52734.2025.01571"},{"key":"16_CR12","unstructured":"Kingma, D.P.: Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114 (2013)"},{"key":"16_CR13","unstructured":"Lai, Z., et\u00a0al.: Hunyuan3d 2.5: towards high-fidelity 3d assets generation with ultimate details. arXiv preprint arXiv:2506.16504 (2025)"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Lan, Y., et al.: Ln3diff: scalable latent neural fields diffusion for speedy 3d generation. In: European Conference on Computer Vision, pp. 112\u2013130. Springer (2025). https:\/\/doi.org\/10.1007\/978-3-031-73235-5_7","DOI":"10.1007\/978-3-031-73235-5_7"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Li, M., Duan, Y., Zhou, J., Lu, J.: Diffusion-sdf: text-to-shape via voxelized diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12642\u201312651 (2023)","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Craftsman: high-fidelity mesh generation with 3d native generation and interactive geometry refiner. arXiv preprint arXiv:2405.14979 (2024)","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Triposg: High-fidelity 3d shape synthesis using large-scale rectified flow models. arXiv preprint arXiv:2502.06608 (2025)","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van Gool, 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":"16_CR19","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3d reconstruction in function space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Nielson, G.M.: Dual marching cubes. In: IEEE visualization, pp. 489\u2013496. IEEE (2004)","DOI":"10.1109\/VISUAL.2004.28"},{"key":"16_CR21","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision, arXiv preprint arXiv:2304.07193 (2023)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"16_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Ren, X., Huang, J., Zeng, X., Museth, K., Fidler, S., Williams, F.: Xcube: large-scale 3d generative modeling using sparse voxel hierarchies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4209\u20134219 (2024)","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"16_CR25","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":"16_CR26","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":"16_CR27","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models, arXiv preprint arXiv:2202.00512 (2022)"},{"issue":"4","key":"16_CR28","first-page":"1","volume":"42","author":"T Shen","year":"2023","unstructured":"Shen, T., et al.: Flexible isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. 42(4), 1\u201337 (2023)","journal-title":"ACM Trans. Graph."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Shue, J.R., Chan, E.R., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3d neural field generation using triplane diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20875\u201320886 (2023)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"16_CR30","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models, arXiv preprint arXiv:2010.02502 (2020)"},{"key":"16_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Direct3d: scalable image-to-3d generation via 3d latent diffusion transformer, arXiv preprint arXiv:2405.14832 (2024)","DOI":"10.52202\/079017-3873"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3d latents for scalable and versatile 3d generation, arXiv preprint arXiv:2412.01506 (2024)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Xiong, B., Wei, S.T., Zheng, X.Y., Cao, Y.P., Lian, Z., Wang, P.S.: Octfusion: Octree-based diffusion models for 3d shape generation, arXiv preprint arXiv:2408.14732 (2024)","DOI":"10.1111\/cgf.70198"},{"key":"16_CR35","unstructured":"Xu, J., Cheng, W., Gao, Y., Wang, X., Gao, S., Shan, Y.: Instantmesh: efficient 3d mesh generation from a single image with sparse-view large reconstruction models, arXiv preprint arXiv:2404.07191 (2024)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: Pointflow: 3d point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Yariv, L., Puny, O., Gafni, O., Lipman, Y.: Mosaic-sdf for 3d generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4630\u20134639 (2024)","DOI":"10.1109\/CVPR52733.2024.00443"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Ye, C., et al.: Hi3dgen: high-fidelity 3d geometry generation from images via normal bridging, vol. 3, arXiv preprint arXiv:2503.22236 (2025)","DOI":"10.1109\/ICCV51701.2025.02323"},{"issue":"4","key":"16_CR39","first-page":"1","volume":"42","author":"B Zhang","year":"2023","unstructured":"Zhang, B., Tang, J., Niessner, M., Wonka, P.: 3dshape2vecset: a 3d shape representation for neural fields and generative diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201316 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"16_CR40","first-page":"1","volume":"43","author":"L Zhang","year":"2024","unstructured":"Zhang, L., et al.: Clay: a controllable large-scale generative model for creating high-quality 3d assets. ACM Trans. Graph. (TOG) 43(4), 1\u201320 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR41","unstructured":"Zhao, Z., et\u00a0al.: Hunyuan3d 2.0: scaling diffusion models for high resolution textured 3d assets generation. arXiv preprint arXiv:2501.12202 (2025)"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Michelangelo: conditional 3d shape generation based on shape-image-text aligned latent representation. Adv. Neural Inform. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-3236"},{"issue":"4","key":"16_CR43","first-page":"1","volume":"42","author":"XY Zheng","year":"2023","unstructured":"Zheng, X.Y., Pan, H., Wang, P.S., Tong, X., Liu, Y., Shum, H.Y.: Locally attentional sdf diffusion for controllable 3d shape generation. ACM Trans. Graph. (ToG) 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph. (ToG)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31335-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T10:59:33Z","timestamp":1785754773000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31335-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"ISBN":["9783032313348","9783032313355"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31335-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"assertion":[{"value":"4 August 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"}}]}}