{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:22:24Z","timestamp":1776453744082,"version":"3.51.2"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2017,11,16]],"date-time":"2017-11-16T00:00:00Z","timestamp":1510790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CHS-1422441, CHS-1617333"],"award-info":[{"award-number":["CHS-1422441, CHS-1617333"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,2,28]]},"abstract":"<jats:p>We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching. The descriptor is produced by a convolutional network that is trained to embed geometrically and semantically similar points close to one another in descriptor space. The network processes surface neighborhoods around points on a shape that are captured at multiple scales by a succession of progressively zoomed-out views, taken from carefully selected camera positions. We leverage two extremely large sources of data to train our network. First, since our network processes rendered views in the form of 2D images, we repurpose architectures pretrained on massive image datasets. Second, we automatically generate a synthetic dense point correspondence dataset by nonrigid alignment of corresponding shape parts in a large collection of segmented 3D models. As a result of these design choices, our network effectively encodes multiscale local context and fine-grained surface detail. Our network can be trained to produce either category-specific descriptors or more generic descriptors by learning from multiple shape categories. Once trained, at test time, the network extracts local descriptors for shapes without requiring any part segmentation as input. Our method can produce effective local descriptors even for shapes whose category is unknown or different from the ones used while training. We demonstrate through several experiments that our learned local descriptors are more discriminative compared to state-of-the-art alternatives and are effective in a variety of shape analysis applications.<\/jats:p>","DOI":"10.1145\/3137609","type":"journal-article","created":{"date-parts":[[2017,11,17]],"date-time":"2017-11-17T14:02:02Z","timestamp":1510927322000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional Networks"],"prefix":"10.1145","volume":"37","author":[{"given":"Haibin","family":"Huang","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, MA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos","family":"Kalogerakis","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, MA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhartha","family":"Chaudhuri","sequence":"additional","affiliation":[{"name":"IIT Bombay, Mumbai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duygu","family":"Ceylan","sequence":"additional","affiliation":[{"name":"Adobe Research, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir G.","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ersin","family":"Yumer","sequence":"additional","affiliation":[{"name":"Adobe Research, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,11,16]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Proceedings of the International Symposium on Advances in Spatial Databases. 207--226","author":"Ankerst M."},{"key":"e_1_2_2_2_1","volume-title":"2011 IEEE International Conference on Computer Vision Workshops.","author":"Aubry M."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.993558"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913514283"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.491"},{"key":"e_1_2_2_6_1","volume-title":"Proceedings of the Symposium on Geometry Processing (SGP\u201915)","author":"Boscaini D."},{"key":"e_1_2_2_7_1","volume-title":"The Conference and Workshop on Neural Information Processing Systems (NIPS\u201916)","author":"Boscaini D."},{"key":"e_1_2_2_8_1","unstructured":"J. Bromley I. Guyon Y. Lecun E. Sackinger and R. Shah. 1994. Signature Verification using a Siamese Time Delay Neural Network. Advances in Neural Information Processing Systems 6. Morgan-Kaufmann. 737--744.   J. Bromley I. Guyon Y. Lecun E. Sackinger and R. Shah. 1994. Signature Verification using a Siamese Time Delay Neural Network. Advances in Neural Information Processing Systems 6. Morgan-Kaufmann. 737--744."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1899404.1899405"},{"key":"e_1_2_2_10_1","unstructured":"A. X. Chang T. A. Funkhouser L. J. Guibas P. Hanrahan Q.-X. Huang Z. Li S. Savarese M. Savva S. Song H. Su J. Xiao L. Yi and F. Yu. 2015. ShapeNet: An information-rich 3D model repository. CoRR.  A. X. Chang T. A. Funkhouser L. J. Guibas P. Hanrahan Q.-X. Huang Z. Li S. Savarese M. Savva S. Song H. Su J. Xiao L. Yi and F. Yu. 2015. ShapeNet: An information-rich 3D model repository. CoRR."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00669"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360641"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122501.1122507"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835487"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_2_2_16_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)","author":"Han X."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508364"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.765655"},{"key":"e_1_2_2_20_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)","author":"Kalogerakis E."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778839"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1057432.1057448"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601117"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461933"},{"key":"e_1_2_2_25_1","volume-title":"Adam: A method for stochastic optimization. CoRR.","author":"Kingma D. P.","year":"2014"},{"key":"e_1_2_2_26_1","volume-title":"The Conference and Workshop on Neural Information Processing Systems (NIPS\u201912)","author":"Krizhevsky A."},{"key":"e_1_2_2_27_1","volume-title":"IEEE International Conference on Robotics and Automation (ICRA\u201914)","author":"Lai K."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-012-0724-x"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12438"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.278"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"e_1_2_2_32_1","volume-title":"IEEE International Conference on Robotics and Automation (ICRA\u201915)","author":"Maturana D."},{"key":"e_1_2_2_33_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Monti F."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/781606.781639"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1877808.1877822"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/571647.571648"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964928"},{"key":"e_1_2_2_38_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Qi C. R."},{"key":"e_1_2_2_39_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916)","author":"Qi C. R."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.532"},{"key":"e_1_2_2_41_1","volume-title":"Eurographics Workshop on 3D Object Retrieval (3DOR\u201917)","author":"Rodola E."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_2_43_1","volume-title":"Symposium on Pattern Recognition. 392--397","author":"Saupe D."},{"key":"e_1_2_2_44_1","volume-title":"Eurographics Workshop on 3D Object Retrieval (3DOR\u201916)","author":"Savva M."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0279-0"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.22"},{"key":"e_1_2_2_47_1","unstructured":"K. Simonyan and A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. CoRR.  K. Simonyan and A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. CoRR."},{"key":"e_1_2_2_48_1","volume-title":"European Conference on Computer Vision (ECCV\u201916)","author":"Sinha A."},{"key":"e_1_2_2_49_1","volume-title":"The Conference and Workshop on Neural Information Processing Systems (NIPS\u201912)","author":"Socher R."},{"key":"e_1_2_2_50_1","volume-title":"European Conference on Computer Vision (ECCV\u201916)","author":"Song S."},{"key":"e_1_2_2_51_1","volume-title":"Proceedings of the Symposium on Geometry Processing (SGP\u201907)","author":"Sorkine O."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276478"},{"key":"e_1_2_2_54_1","volume-title":"European Conference on Computer Vision (ECCV\u201910)","author":"Tombari F."},{"key":"e_1_2_2_55_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916)","author":"Wei L."},{"key":"e_1_2_2_56_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915). 1912","author":"Wu Z.","year":"1920"},{"key":"e_1_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Y. Xian B. Schiele and Z. Akata. 2017. Zero-shot learning - The good the bad and the ugly. CoRR (2017).  Y. Xian B. Schiele and Z. Akata. 2017. Zero-shot learning - The good the bad and the ugly. CoRR (2017).","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_2_2_58_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)","author":"Xie J."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988458.2988473"},{"key":"e_1_2_2_60_1","volume-title":"European Conference on Computer Vision (ECCV\u201916)","author":"Yi K. M."},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_2_2_62_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Yi L."},{"key":"e_1_2_2_63_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Zeng A."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1037957.1037958"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3137609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3137609","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3137609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:10Z","timestamp":1750212670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3137609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,16]]},"references-count":64,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,2,28]]}},"alternative-id":["10.1145\/3137609"],"URL":"https:\/\/doi.org\/10.1145\/3137609","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,16]]},"assertion":[{"value":"2017-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-11-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}