{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:49:00Z","timestamp":1765547340033,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729393"},{"type":"electronic","value":"9783031729409"}],"license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72940-9_6","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T20:42:34Z","timestamp":1731789754000},"page":"92-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DoughNet: A Visual Predictive Model for\u00a0Topological Manipulation of\u00a0Deformable Objects"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1260-1319","authenticated-orcid":false,"given":"Dominik","family":"Bauer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8217-4818","authenticated-orcid":false,"given":"Zhenjia","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8768-7356","authenticated-orcid":false,"given":"Shuran","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,17]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bartsch, A., Avra, C., Farimani, A.B.: Sculptbot: pre-trained models for 3D deformable object manipulation. arXiv preprint arXiv:2309.08728 (2023)","DOI":"10.1109\/ICRA57147.2024.10610899"},{"key":"6_CR2","unstructured":"Bathe, K.J.: Finite Element Procedures. Klaus-Jurgen Bathe (2006)"},{"key":"6_CR3","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. NIPS 28 (2015)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Nguyen, V., Han, F., Kiveris, R., Tu, Z.: Topology-aware single-image 3D shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 270\u2013271 (2020)","DOI":"10.1109\/CVPRW50498.2020.00143"},{"key":"6_CR5","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. NeurIPS 34, 17864\u201317875 (2021)","journal-title":"NeurIPS"},{"key":"6_CR6","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning (2016)"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT De Boer","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134, 19\u201367 (2005)","journal-title":"Ann. Oper. Res."},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Denninger, M., et al.: Blenderproc2: a procedural pipeline for photorealistic rendering. J. Open Source Softw. 8(82), 4901 (2023). https:\/\/doi.org\/10.21105\/joss.0490","DOI":"10.21105\/joss.0490"},{"key":"6_CR9","unstructured":"Driess, D., Huang, Z., Li, Y., Tedrake, R., Toussaint, M.: Learning Multi-object Dynamics With Compositional Neural Radiance Fields, pp. 1755\u20131768 (2023)"},{"key":"6_CR10","unstructured":"Gibson, S.F.F.: Constrained elastic surfacenets: generating smooth models from binary segmented data. TR99 24 (1999)"},{"key":"6_CR11","unstructured":"Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. In: ICLR (2019)"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Heiden, E., Macklin, M., Narang, Y.S., Fox, D., Garg, A., Ramos, F.: DiSECt: a differentiable simulation engine for autonomous robotic cutting. In: RSS. Virtual (2021). https:\/\/doi.org\/10.15607\/RSS.2021.XVII.067","DOI":"10.15607\/RSS.2021.XVII.067"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: A moving least squares material point method with displacement discontinuity and two-way rigid body coupling. ACM Trans. Graph. 37(4), 150 (2018)","DOI":"10.1145\/3197517.3201293"},{"issue":"6","key":"6_CR14","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1145\/3355089.3356506","volume":"38","author":"Y Hu","year":"2019","unstructured":"Hu, Y., Li, T.M., Anderson, L., Ragan-Kelley, J., Durand, F.: Taichi: a language for high-performance computation on spatially sparse data structures. ACM TOG 38(6), 201 (2019)","journal-title":"ACM TOG"},{"issue":"1","key":"6_CR15","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","volume":"35","author":"PJ Huber","year":"1964","unstructured":"Huber, P.J.: Robust estimation of a location parameter. Ann. Math. Stat. 35(1), 73\u2013101 (1964)","journal-title":"Ann. Math. Stat."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Ju, T., Losasso, F., Schaefer, S., Warren, J.: Dual contouring of hermite data. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 339\u2013346 (2002)","DOI":"10.1145\/566570.566586"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Le Cleac\u2019h, S., et al.: Differentiable physics simulation of dynamics-augmented neural objects. RAL 8(5), 2780\u20132787 (2023)","DOI":"10.1109\/LRA.2023.3257707"},{"key":"6_CR18","unstructured":"Li, S., et al.: Dexdeform: dexterous deformable object manipulation with human demonstrations and differentiable physics. arXiv preprint arXiv:2304.03223 (2023)"},{"key":"6_CR19","unstructured":"Li, X., et al.: Pac-nerf: physics augmented continuum neural radiance fields for geometry-agnostic system identification. In: ICLR (2022)"},{"key":"6_CR20","unstructured":"Li, Y., et al.: Visual grounding of learned physical models. In: ICML (2020)"},{"key":"6_CR21","unstructured":"Li, Y., Wu, J., Tedrake, R., Tenenbaum, J.B., Torralba, A.: Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. In: ICLR (2019)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR23","unstructured":"Lin, X., Huang, Z., Li, Y., Tenenbaum, J.B., Held, D., Gan, C.: Diffskill: skill abstraction from differentiable physics for deformable object manipulations with tools. In: ICLR (2022)"},{"key":"6_CR24","unstructured":"Lin, X., et al.: Planning with spatial-temporal abstraction from point clouds for deformable object manipulation. In: CoRL (2022)"},{"issue":"4","key":"6_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601152","volume":"33","author":"M Macklin","year":"2014","unstructured":"Macklin, M., M\u00fcller, M., Chentanez, N., Kim, T.Y.: Unified particle physics for real-time applications. ACM Trans. Graph. 33(4), 1\u201312 (2014)","journal-title":"ACM Trans. Graph."},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Matl, C., Bajcsy, R.: Deformable elasto-plastic object shaping using an elastic hand and model-based reinforcement learning. In: IROS, pp. 3955\u20133962 (2021)","DOI":"10.1109\/IROS51168.2021.9636808"},{"key":"6_CR27","unstructured":"Van\u00a0der Merwe, M., Berenson, D., Fazeli, N.: Learning the dynamics of compliant tool-environment interaction for visuo-tactile contact servoing. In: CoRL, pp. 2052\u20132061 (2023)"},{"issue":"1","key":"6_CR28","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":"6_CR29","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: CVPR, pp. 165\u2013174 (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"6_CR30","volume-title":"An improved algorithm for finding the strongly connected components of a directed graph","author":"DJ Pearce","year":"2005","unstructured":"Pearce, D.J.: An improved algorithm for finding the strongly connected components of a directed graph. Victoria University, Wellington, NZ, Tech. Rep (2005)"},{"key":"6_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"issue":"4","key":"6_CR32","first-page":"9857","volume":"7","author":"C Qi","year":"2022","unstructured":"Qi, C., Lin, X., Held, D.: Learning closed-loop dough manipulation using a differentiable reset module. RAL 7(4), 9857\u20139864 (2022)","journal-title":"RAL"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Schmidt, F.: Generalization in generation: a closer look at exposure bias. arXiv preprint arXiv:1910.00292 (2019)","DOI":"10.18653\/v1\/D19-5616"},{"key":"6_CR34","unstructured":"Seo, Y., et al.: Masked world models for visual control. In: CoRL, pp. 1332\u20131344 (2023)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Shen, B., et al.: Acid: action-conditional implicit visual dynamics for deformable object manipulation. In: RSS (2022)","DOI":"10.15607\/RSS.2022.XVIII.001"},{"key":"6_CR36","unstructured":"Shi, H., Xu, H., Clarke, S., Li, Y., Wu, J.: Robocook: long-horizon elasto-plastic object manipulation with diverse tools. arXiv preprint arXiv:2306.14447 (2023)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Shi, H., Xu, H., Huang, Z., Li, Y., Wu, J.: Robocraft: learning to see, simulate, and shape elasto-plastic objects with graph networks. In: RSS (2022)","DOI":"10.15607\/RSS.2022.XVIII.008"},{"issue":"1\u20132","key":"6_CR38","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/0045-7825(94)90112-0","volume":"118","author":"D Sulsky","year":"1994","unstructured":"Sulsky, D., Chen, Z., Schreyer, H.L.: A particle method for history-dependent materials. Comput. Methods Appl. Mech. Eng. 118(1\u20132), 179\u2013196 (1994)","journal-title":"Comput. Methods Appl. Mech. Eng."},{"issue":"2","key":"6_CR39","doi-asserted-by":"publisher","first-page":"413","DOI":"10.3390\/s21020413","volume":"21","author":"M T\u00f6lgyessy","year":"2021","unstructured":"T\u00f6lgyessy, M., Dekan, M., Chovanec, L., Hubinsk\u1ef3, P.: Evaluation of the azure kinect and its comparison to kinect v1 and kinect v2. Sensors 21(2), 413 (2021)","journal-title":"Sensors"},{"key":"6_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wi, Y., Florence, P., Zeng, A., Fazeli, N.: Virdo: visio-tactile implicit representations of deformable objects. In: ICRA, pp. 3583\u20133590 (2022)","DOI":"10.1109\/ICRA46639.2022.9812097"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wi, Y., Zeng, A., Florence, P., Fazeli, N.: Virdo++: real-world, visuo-tactile dynamics and perception of deformable objects. In: CoRL (2022)","DOI":"10.1109\/ICRA46639.2022.9812097"},{"key":"6_CR43","unstructured":"You, Y., Shen, B., Deng, C., Geng, H., Wang, H., Guibas, L.: Make a donut: language-guided hierarchical EMD-space planning for zero-shot deformable object manipulation. arXiv preprint arXiv:2311.02787 (2023)"},{"key":"6_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, B., Tang, J., Nie\u00dfner, M., Wonka, P.: 3dshape2vecset: a 3D shape representation for neural fields and generative diffusion models. ACM Trans. Graph. 42(4), 1\u201316 (2023). https:\/\/doi.org\/10.1145\/3592442","DOI":"10.1145\/3592442"},{"key":"6_CR45","unstructured":"Zhao, Z., et al.: Michelangelo: conditional 3D shape generation based on shape-image-text aligned latent representation. arXiv preprint arXiv:2306.17115 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72940-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T21:32:11Z","timestamp":1731792731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72940-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"ISBN":["9783031729393","9783031729409"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72940-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,17]]},"assertion":[{"value":"17 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}