{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:03:47Z","timestamp":1789319027560,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368386","type":"print"},{"value":"9783032368393","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\/978-3-032-36839-3_33","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:25:46Z","timestamp":1789316746000},"page":"607-625","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["R3DP: Real-Time 3D-Aware Policy for\u00a0Embodied Manipulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3370-9258","authenticated-orcid":false,"given":"Yuhao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0239-4548","authenticated-orcid":false,"given":"Wanxi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7362-6384","authenticated-orcid":false,"given":"Yue","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6137-0367","authenticated-orcid":false,"given":"Yi","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6688-8418","authenticated-orcid":false,"given":"Jingnan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2481-3267","authenticated-orcid":false,"given":"Qiaochu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5831-2739","authenticated-orcid":false,"given":"Yaxing","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6815-9866","authenticated-orcid":false,"given":"Zhixuan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2925-7798","authenticated-orcid":false,"given":"Yibin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2619-8827","authenticated-orcid":false,"given":"Congsheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2822-4690","authenticated-orcid":false,"given":"Xianda","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5182-5621","authenticated-orcid":false,"given":"Wei","family":"Sui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6158-6277","authenticated-orcid":false,"given":"Yaohui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5429-3177","authenticated-orcid":false,"given":"Yanyan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0321-021X","authenticated-orcid":false,"given":"Yao","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"33_CR1","unstructured":"Abouzeid, A., Mansour, M., Sun, Z., Song, D.: GeoAware-VLA: implicit geometry aware vision-language-action model (2025). arXiv preprint arXiv:2509.14117"},{"key":"33_CR2","unstructured":"Black, K., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. In: 9th Annual Conference on Robot Learning (2025)"},{"key":"33_CR3","unstructured":"Black, K., et\u00a0al.: $$\\pi _0$$: a vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Cabon, Y., et al.: MuSt3R: multi-view network for stereo 3D reconstruction. In: CVPR, pp. 1050\u20131060 (2025)","DOI":"10.1109\/CVPR52734.2025.00106"},{"key":"33_CR5","unstructured":"Chen, T., et\u00a0al.: Robotwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088 (2025)"},{"issue":"10\u201311","key":"33_CR6","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robot. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Robot. Res."},{"key":"33_CR7","unstructured":"Deng, T., et al.: What is the best 3D scene representation for robotics? from geometric to foundation models. arXiv preprint arXiv:2512.03422 (2025)"},{"key":"33_CR8","unstructured":"Deng, T., et al.: Reloc-VGGT: visual re-localization with geometry grounded transformer (2025)"},{"key":"33_CR9","unstructured":"Dinh\u00a0Vuong, A., Nhat\u00a0Vu, M., Reid, I.: Improving robotic manipulation with efficient geometry-aware vision encoder. arXiv e-prints, pp. arXiv\u20132509 (2025)"},{"key":"33_CR10","unstructured":"Fang, X., et al.: Dens3R: a foundation model for 3d geometry prediction. arXiv preprint arXiv:2507.16290 (2025)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"33_CR12","unstructured":"Gao, J., et al.: More: 3D visual geometry reconstruction meets mixture-of-experts. arXiv preprint arXiv:2510.27234 (2025)"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Gong, Z., et al.: CARP: visuomotor policy learning via coarse-to-fine autoregressive prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13460\u201313470 (2025)","DOI":"10.1109\/ICCV51701.2025.01250"},{"key":"33_CR14","unstructured":"Grotz, M., Shridhar, M., Chao, Y.W., Asfour, T., Fox, D.: Peract2: benchmarking and learning for robotic bimanual manipulation tasks. In: CoRL 2024 Workshop on Whole-body Control and Bimanual Manipulation: Applications in Humanoids and Beyond (2024)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Jang, W., Weinzaepfel, P., Leroy, V., Agapito, L., Revaud, J.: Pow3R: Empowering unconstrained 3D reconstruction with camera and scene priors. In: CVPR, pp. 1071\u20131081 (2025)","DOI":"10.1109\/CVPR52734.2025.00108"},{"key":"33_CR16","unstructured":"Ke, T.W., Gkanatsios, N., Fragkiadaki, K.: 3D diffuser actor: policy diffusion with 3D scene representations. arXiv preprint arXiv:2402.10885 (2024)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3d with mast3r. In: ECCV, vol. 15130, pp. 71\u201391 (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Cameras as relative positional encoding. arXiv preprint arXiv:2507.10496 (2025)","DOI":"10.52202\/085713-0540"},{"key":"33_CR19","unstructured":"Lin, T., Li, G., Zhong, Y., Zou, Y., Zhao, B.: Evo-0: vision-language-action model with implicit spatial understanding (2025). arXiv preprint arXiv:2507.00416"},{"key":"33_CR20","unstructured":"Lin, X., et al.: Sem: enhancing spatial understanding for robust robot manipulation. arXiv preprint arXiv:2505.16196 (2025)"},{"key":"33_CR21","unstructured":"Liu, S., et al.: RDT-1B: a diffusion foundation model for bimanual manipulation. arXiv preprint arXiv:2410.07864 (2024)"},{"key":"33_CR22","unstructured":"Lu, Y., et al.: H$$^3$$DP: triply-hierarchical diffusion policy for visuomotor learning. arXiv preprint arXiv:2505.07819 (2025)"},{"key":"33_CR23","unstructured":"Ma, J., et al.: CDP: Towards robust autoregressive visuomotor policy learning via causal diffusion. arXiv preprint arXiv:2506.14769 (2025)"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Manuelli, L., Gao, W., Florence, P., Tedrake, R.: KPAM: KeyPoint Affordances for Category-Level Robotic Manipulation. In: The International Symposium of Robotics Research, pp. 132\u2013157 (2019)","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"33_CR25","unstructured":"Miyato, T., Jaeger, B., Welling, M., Geiger, A.: GTA: a geometry-aware attention mechanism for multi-view transformers. arXiv preprint arXiv:2310.10375 (2023)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Mu, Y., et al.: Robotwin: dual-arm robot benchmark with generative digital twins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 27649\u201327660 (2025)","DOI":"10.1109\/CVPR52734.2025.02575"},{"key":"33_CR27","unstructured":"Nair, S., Rajeswaran, A., Kumar, V., Finn, C., Gupta, A.: R3M: a universal visual representation for robot manipulation. arXiv preprint arXiv:2203.12601 (2022)"},{"key":"33_CR28","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"33_CR29","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models: Open X-embodiment collaboration 0. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"33_CR30","unstructured":"Pearce, T., et al.: Imitating human behaviour with diffusion models. arXiv preprint arXiv:2301.10677 (2023)"},{"key":"33_CR31","unstructured":"Qian, Q., et al.: GP3: a 3D geometry-aware policy with multi-view images for robotic manipulation. arXiv preprint arXiv:2509.15733 (2025)"},{"key":"33_CR32","doi-asserted-by":"publisher","unstructured":"Qu, D., et al.: SpatialVLA: exploring Spatial Representations for Visual-Language-Action Models. In: Proceedings of Robotics: Science and Systems. LosAngeles, CA, USA (2025). https:\/\/doi.org\/10.15607\/RSS.2025.XXI.011","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"33_CR33","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning, pp. 785\u2013799. PMLR (2023)"},{"key":"33_CR34","unstructured":"Shukor, M., et al.: SmolVLA: a vision-language-action model for affordable and efficient robotics. arXiv preprint arXiv:2506.01844 (2025)"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: MV-DUSt3R+: single-stage scene reconstruction from sparse views in 2 seconds. In: CVPR, pp. 5283\u20135293 (2025)","DOI":"10.1109\/CVPR52734.2025.00498"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. In: 3DV (2025)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: VGGT: Visual Geometry Grounded Transformer. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: Geometric 3D vision made easy. In: CVPR, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"33_CR40","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: scalable permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3R: Towards 3D reconstruction of 1000+ images in one forward pass. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"33_CR43","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR44","doi-asserted-by":"crossref","unstructured":"Ze, Y., et al.: Generalizable humanoid manipulation with 3D diffusion policies. arXiv preprint arXiv:2410.10803 (2024)","DOI":"10.1109\/IROS60139.2025.11246340"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Ze, Y., et al.: 3D diffusion policy: generalizable visuomotor policy learning via simple 3D representations. In: Proceedings of Robotics: Science and Systems (RSS) (2024)","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"33_CR46","unstructured":"Zeng, A., et al.: Transporter networks: rearranging the visual world for robotic manipulation. arXiv preprint arXiv:2010.14406 (2020)"},{"key":"33_CR47","unstructured":"Zhang, J., et al.: MonST3R: a simple approach for estimating geometry in the presence of motion. In: ICLR (2025)"},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Flare: feed-forward geometry, appearance and camera estimation from uncalibrated sparse views. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint arXiv:2304.13705 (2023)","DOI":"10.15607\/RSS.2023.XIX.016"}],"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\/978-3-032-36839-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:25:54Z","timestamp":1789316754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36839-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368386","9783032368393"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36839-3_33","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":"14 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"}}]}}