{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:13:01Z","timestamp":1789074781707,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368454","type":"print"},{"value":"9783032368461","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\/978-3-032-36846-1_6","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:44Z","timestamp":1789074164000},"page":"92-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CanoVerse: 3D Object Scalable Canonicalization and\u00a0Dataset for\u00a0Generation and\u00a0Pose"],"prefix":"10.1007","author":[{"given":"Li","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dehao","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanghui","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingda","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueying","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"6_CR1","unstructured":"Chang, A.X., et al.: ShapeNet: an Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR], Stanford University \u2014 Princeton University \u2014 Toyota Technological Institute at Chicago (2015)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Dora: Sampling and benchmarking for 3D shape variational auto-encoders. arXiv preprint arXiv:2412.17808 (2024)","DOI":"10.1109\/CVPR52734.2025.01515"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: European Conference on Computer Vision, pp. 139\u2013156. Springer (2020)","DOI":"10.1007\/978-3-030-58574-7_9"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Secondpose: Se (3)-consistent dual-stream feature fusion for category-level pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9959\u20139969 (2024)","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Dai, Q., et al.: Domain randomization-enhanced depth simulation and restoration for perceiving and grasping specular and transparent objects. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19842-7_22"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Di, Y., et al.: Shapematcher: Self-supervised joint shape canonicalization segmentation retrieval and deformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21017\u201321028 (2024)","DOI":"10.1109\/CVPR52733.2024.01986"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3d scanned household items (2022). https:\/\/arxiv.org\/abs\/2204.11918","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: Object level depth reconstruction for category level 6d object pose estimation from monocular RGB image. In: European Conference on Computer Vision, pp. 220\u2013236. Springer (2022)","DOI":"10.1007\/978-3-031-20086-1_13"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Fu, H., Cohen-Or, D., Dror, G., Sheffer, A.: Upright orientation of man-made objects. ACM Trans. Graph. 27(3), 42 (2008) https:\/\/doi.org\/10.1145\/1360612.1360641","DOI":"10.1145\/1360612.1360641"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Han, X., et al.: Frontiers and prospects of 3D reconstruction and generation. J. Image Graph. 31(6), 2182\u20132197 (2026).https:\/\/doi.org\/10.11834\/jig.260070. received: 2026-01-29; Revised: 2026-03-09; Published: 2026-06-16","DOI":"10.11834\/jig.260070"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Jin, L., et al.: One-shot 3D object canonicalization based on geometric and semantic consistency. In: CVPR, pp. 16850\u201316859 (2025)","DOI":"10.1109\/CVPR52734.2025.01570"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Lee, T., Wen, B., Kang, M., Kang, G., Kweon, I.S., Yoon, K.J.: Any6d: model-free 6d pose estimation of novel objects. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11633\u201311643 (2025)","DOI":"10.1109\/CVPR52734.2025.01086"},{"key":"6_CR13","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":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lin, J., Wei, Z., Ding, C., Jia, K.: Category-level 6d object pose and size estimation using self-supervised deep prior deformation networks. In: European Conference on Computer Vision, pp. 19\u201334. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_2"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Wei, Z., Zhang, Y., Jia, K.: Vi-net: boosting category-level 6d object pose estimation via learning decoupled rotations on the spherical representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14001\u201314011 (2023)","DOI":"10.1109\/ICCV51070.2023.01287"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Lin, X., et al.: Cleanpose: category-level object pose estimation via causal learning and knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.00566"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Lin, X., Yang, W., Gao, Y., Zhang, T.: Instance-adaptive and geometric-aware keypoint learning for category-level 6d object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21040\u201321049 (2024)","DOI":"10.1109\/CVPR52733.2024.01988"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Orientation matters: making 3d generative models orientation-aligned (2025). https:\/\/arxiv.org\/abs\/2506.08640","DOI":"10.52202\/085713-4968"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Ma, Z., Yue, Y., Gkioxari, G.: Find any part in 3D (2024). https:\/\/arxiv.org\/abs\/2411.13550","DOI":"10.1109\/ICCV51701.2025.00733"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: pixel-wise voting network for 6d of pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"6_CR21","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":"6_CR22","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":"6_CR23","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":"6_CR24","doi-asserted-by":"crossref","unstructured":"Sajnani, R., Poulenard, A., Jain, J., Dua, R., Guibas, L.J., Sridhar, S.: Condor: self-supervised canonicalization of 3D pose for partial shapes. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01646"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Stojanov, S., Thai, A., Rehg, J.M.: Using shape to categorize: low-shot learning with an explicit shape bias (2021)","DOI":"10.1109\/CVPR46437.2021.00184"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: Onepose: one-shot object pose estimation without cad models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6825\u20136834 (2022)","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"6_CR27","unstructured":"Sun, W., et al.: Canonical capsules: self-supervised capsules in canonical pose. In: Neural Information Processing Systems (2021)"},{"key":"6_CR28","unstructured":"Team, Q.: Qwen2.5-vl (2025). https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"6_CR29","unstructured":"Team, T.H.: Hunyuan3d 2.1: from images to high-fidelity 3d assets with production-ready PBR material (2025)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"6_CR31","unstructured":"Wang, Z., Zhang, Z., Pang, T., Du, C., Zhao, H., Zhao, Z.: Orient anything: learning robust object orientation estimation from rendering 3d models. arXiv:2412.18605 (2024)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: Foundationpose: unified 6d pose estimation and tracking of novel objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17868\u201317879 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"6_CR33","doi-asserted-by":"publisher","first-page":"121859","DOI":"10.52202\/079017-3873","volume":"37","author":"S Wu","year":"2024","unstructured":"Wu, S., et al.: Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer. Adv. Neural. Inf. Process. Syst. 37, 121859\u2013121881 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Direct3d-s2: gigascale 3d generation made easy with spatial sparse attention. arXiv preprint arXiv:2505.17412 (2025)","DOI":"10.52202\/085713-5688"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Omniobject3d: large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"6_CR36","unstructured":"Wu, Z., et al.: 3d shapenets: a deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)"},{"key":"6_CR37","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":"6_CR38","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: Ulip-2: towards scalable multimodal pre-training for 3d understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27091\u201327101 (2024)","DOI":"10.1109\/CVPR52733.2024.02558"},{"issue":"4","key":"6_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 Transactions On Graphics (TOG) 42(4), 1\u201316 (2023)","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Omni6dpose: A benchmark and model for universal 6d object pose estimation and tracking. In: European Conference on Computer Vision, pp. 199\u2013216. Springer (2024)","DOI":"10.1007\/978-3-031-73226-3_12"},{"issue":"4","key":"6_CR41","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":"6_CR42","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"6_CR43","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":"6_CR44","unstructured":"Zhou, J., Wang, J., Ma, B., Liu, Y.S., Huang, T., Wang, X.: Uni3d: exploring unified 3d representation at scale. In: International Conference on Learning Representations (ICLR) (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36846-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:51Z","timestamp":1789074171000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36846-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368454","9783032368461"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36846-1_6","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":"11 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}