{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T10:48:13Z","timestamp":1782470893952,"version":"3.54.5"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032009852","type":"print"},{"value":"9783032009869","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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\/978-3-032-00986-9_19","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T23:26:56Z","timestamp":1759274816000},"page":"275-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Pose Awareness and\u00a03D Consistency in\u00a0Semantic Matching"],"prefix":"10.1007","author":[{"given":"Paolo","family":"Sebeto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Baptiste","family":"Weibel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Hartl-Nesic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Vincze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Ausserlechner, P., Haberger, D., Thalhammer, S., Weibel, J.B., Vincze, M.: ZS6D: zero-shot 6d object pose estimation using vision transformers. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 463\u2013469. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611464"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"19_CR3","first-page":"9011","volume":"34","author":"S Cho","year":"2021","unstructured":"Cho, S., Hong, S., Jeon, S., Lee, Y., Sohn, K., Kim, S.: CATs: cost aggregation transformers for visual correspondence. Adv. Neural. Inf. Process. Syst. 34, 9011\u20139023 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Cho, S., Hong, S., Kim, S.: CATs++: boosting cost aggregation with convolutions and transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3218727"},{"key":"19_CR5","unstructured":"Denninger, M., et al.: BlenderProc: reducing the reality gap with photorealistic rendering. In: 16th Robotics: Science and Systems, RSS 2020, Workshops (2020)"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, pp. 178\u2013178 (2004). https:\/\/doi.org\/10.1109\/CVPR.2004.383","DOI":"10.1109\/CVPR.2004.383"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Q., Atanasov, N.: Fully convolutional geometric features for category-level object alignment. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8492\u20138498. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341550"},{"key":"19_CR8","unstructured":"Florence, P.R., Manuelli, L., Tedrake, R.: Dense object nets: Learning dense visual object descriptors by and for robotic manipulation. arXiv preprint arXiv:1806.08756 (2018)"},{"key":"19_CR9","unstructured":"Fu, S., Hamilton, M., Brandt, L.E., Feldmann, A., Zhang, Z., Freeman, W.T.: FeatUp: A model-agnostic framework for features at any resolution (2024)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Goodwin, W., Vaze, S., Havoutis, I., Posner, I.: Zero-shot category-level object pose estimation. In: European Conference on Computer Vision, pp. 516\u2013532. Springer (2022)","DOI":"10.1007\/978-3-031-19842-7_30"},{"key":"19_CR11","unstructured":"Hadjivelichkov, D., Zwane, S., Agapito, L., Deisenroth, M.P., Kanoulas, D.: One-shot transfer of affordance regions? Affcorrs! In: Conference on Robot Learning, pp. 550\u2013560. PMLR (2023)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow: semantic correspondences from object proposals. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1711\u20131725 (2017). https:\/\/api.semanticscholar.org\/CorpusID:6050505","DOI":"10.1109\/TPAMI.2017.2724510"},{"issue":"11","key":"19_CR13","doi-asserted-by":"publisher","first-page":"4011","DOI":"10.1109\/TCAD.2023.3274922","volume":"42","author":"M Han","year":"2023","unstructured":"Han, M., et al.: QuickFPS: architecture and algorithm co-design for farthest point sampling in large-scale point clouds. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 42(11), 4011\u20134024 (2023). https:\/\/doi.org\/10.1109\/TCAD.2023.3274922","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"issue":"2","key":"19_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3292482","volume":"38","author":"M He","year":"2019","unstructured":"He, M., Liao, J., Chen, D., Yuan, L., Sander, P.V.: Progressive color transfer with dense semantic correspondences. ACM Trans. Graph. (TOG) 38(2), 1\u201318 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"19_CR15","unstructured":"Hong, S., Cho, S., Kim, S., Lin, S.: Unifying feature and cost aggregation with transformers for semantic and visual correspondence. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=fQHb1uZzl7"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Jiang, H., Zhu, Y.: Doduo: learning dense visual correspondence from unsupervised semantic-aware flow. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 12420\u201312427. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611587"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Ju, Y., Hu, K., Zhang, G., Zhang, G., Jiang, M., Xu, H.: Robo-ABC: Affordance generalization beyond categories via semantic correspondence for robot manipulation. arXiv preprint arXiv:2401.07487 (2024)","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Jung, H., et\u00a0al.: HouseCat6D-a large-scale multi-modal category level 6d object perception dataset with household objects in realistic scenarios. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22498\u201322508 (2024)","DOI":"10.1109\/CVPR52733.2024.02123"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492\u20139502 (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Jeong, S., Kim, S., Jeon, S., Sohn, K.: Semantic attribute matching networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12339\u201312348 (2019)","DOI":"10.1109\/CVPR.2019.01262"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNet: learning object-aware semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., Lee, Y., Kim, D., Chang, J., Choo, J.: Reference-based sketch image colorization using augmented-self reference and dense semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5801\u20135810 (2020)","DOI":"10.1109\/CVPR42600.2020.00584"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Li, S., Han, K., Costain, T.W., Howard-Jenkins, H., Prisacariu, V.: Correspondence networks with adaptive neighbourhood consensus. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Min, J., Cho, M.: Convolutional hough matching networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2940\u20132950 (June 2021)","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"19_CR25","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: SPair-71k: A large-scale benchmark for semantic correspondence. arXiv prepreint arXiv:1908.10543 (2019)"},{"key":"19_CR26","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2023)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Peebles, W., Zhu, J.Y., Zhang, R., Torralba, A., Efros, A.A., Shechtman, E.: Gan-supervised dense visual alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13470\u201313481 (2022)","DOI":"10.1109\/CVPR52688.2022.01311"},{"key":"19_CR28","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"19_CR29","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":"19_CR30","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.52202\/075280-0068","volume":"36","author":"L Tang","year":"2023","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. Adv. Neural. Inf. Process. Syst. 36, 1363\u20131389 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Taniai, T., Sinha, S.N., Sato, Y.: Joint recovery of dense correspondence and cosegmentation in two images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4246\u20134255 (2016)","DOI":"10.1109\/CVPR.2016.460"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Tsagkas, N., Rome, J., Ramamoorthy, S., Mac\u00a0Aodha, O., Lu, C.X.: Click to grasp: Zero-shot precise manipulation via visual diffusion descriptors. arXiv preprint arXiv:2403.14526 (2024)","DOI":"10.1109\/IROS58592.2024.10801488"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Bar-Tal, O., Bagon, S., Dekel, T.: Splicing ViT features for semantic appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10748\u201310757 (2022)","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"19_CR34","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"19_CR35","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"19_CR36","unstructured":"Yang, L., et al.: Depth anything v2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Telling left from right: identifying geometry-aware semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3076\u20133085 (2024)","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: A tale of two features: stable diffusion complements DINO for zero-shot semantic correspondence. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1973"}],"container-title":["Communications in Computer and Information Science","Robotics, Computer Vision and Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-00986-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T09:57:09Z","timestamp":1782467829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-00986-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783032009852","9783032009869"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-00986-9_19","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ROBOVIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Robotics, Computer Vision and Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 February 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 February 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robovis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/robovis.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}