{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:25:15Z","timestamp":1783661115127,"version":"3.55.0"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s11263-024-02090-y","type":"journal-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T02:01:17Z","timestamp":1715392877000},"page":"4305-4326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Exploring the Usage of Pre-trained Features for Stereo Matching"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6321-1593","authenticated-orcid":false,"given":"Jiawei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0502-168X","authenticated-orcid":false,"given":"Lei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8561-9299","authenticated-orcid":false,"given":"Xiao","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5218-9250","authenticated-orcid":false,"given":"Jin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7419-6240","authenticated-orcid":false,"given":"Lin","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4496-2028","authenticated-orcid":false,"given":"Edwin","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"2090_CR1","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization, arXiv preprint arXiv:1607.06450."},{"key":"2090_CR2","doi-asserted-by":"crossref","unstructured":"Bangunharcana, A., Cho, J. W., Lee, S., Kweon, I. S., Kim, K.-S., & Kim, S. (2021). Correlate-and-excite: Real-time stereo matching via guided cost volume excitation. In 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 3542\u20133548). IEEE.","DOI":"10.1109\/IROS51168.2021.9635909"},{"key":"2090_CR3","unstructured":"Biswas, J., & Veloso, M. (2011). Depth camera based localization and navigation for indoor mobile robots. In RGB-D workshop at RSS (vol. 2011), no.\u00a021."},{"key":"2090_CR4","first-page":"1","volume":"11","author":"M Bleyer","year":"2011","unstructured":"Bleyer, M., Rhemann, C., & Rother, C. (2011). Patchmatch stereo\u2013stereo matching with slanted support windows. Bmvc, 11, 1\u201311.","journal-title":"Bmvc"},{"key":"2090_CR5","doi-asserted-by":"crossref","unstructured":"Cai, C., Poggi, M., Mattoccia, S., & Mordohai, P. (2020). Matching-space stereo networks for cross-domain generalization. In 2020 International conference on 3D vision (3DV) (pp. 364\u2013373). IEEE.","DOI":"10.1109\/3DV50981.2020.00046"},{"key":"2090_CR6","first-page":"66","volume":"6","author":"C Cao","year":"2022","unstructured":"Cao, C., Ren, X., & Fu, Y. (2022). Mvsformer: Multi-view stereo by learning robust image features and temperature-based depth. Transactions on Machine Learning Research, 6, 66.","journal-title":"Transactions on Machine Learning Research"},{"key":"2090_CR7","doi-asserted-by":"crossref","unstructured":"Chang, J.-R., & Chen, Y.-S. (2018). Pyramid stereo matching network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5410\u20135418).","DOI":"10.1109\/CVPR.2018.00567"},{"issue":"10","key":"2090_CR8","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.1109\/TPAMI.2019.2947374","volume":"42","author":"X Cheng","year":"2019","unstructured":"Cheng, X., Wang, P., & Yang, R. (2019). Learning depth with convolutional spatial propagation network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(10), 2361\u20132379.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR9","unstructured":"Cheng, X., Zhong, Y., Harandi, M., Dai, Y., Chang, X., Li, H., Drummond, T., & Ge, Z. (2020). Hierarchical neural architecture search for deep stereo matching. Advances in Neural Information Processing Systems, 33, 22158\u201322169."},{"key":"2090_CR10","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., & Shen, C. (2021). Twins: Revisiting the design of spatial attention in vision transformers. Advances in Neural Information Processing Systems, 34, 9355\u20139366.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2090_CR11","first-page":"66","volume":"6","author":"W Chuah","year":"2023","unstructured":"Chuah, W., Tennakoon, R., Hoseinnezhad, R., Suter, D., & Bab-Hadiashar, A. (2023). An information-theoretic method to automatic shortcut avoidance and domain generalization for dense prediction tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 66.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2090_CR13","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhu, Q., Liu, X., Yuan, W., Zhang, H., & Zhang, C. (2022). Kd-mvs: Knowledge distillation based self-supervised learning for multi-view stereo. In European conference on computer vision (pp. 630\u2013646). Berlin: Springer.","DOI":"10.1007\/978-3-031-19821-2_36"},{"key":"2090_CR14","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. & Uszkoreit, J. (2020). An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929."},{"key":"2090_CR15","doi-asserted-by":"crossref","unstructured":"Engel, J., St\u00fcckler, J., & Cremers, D. (2015). Large-scale direct slam with stereo cameras. In 2015 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 1935\u20131942). IEEE.","DOI":"10.1109\/IROS.2015.7353631"},{"key":"2090_CR16","doi-asserted-by":"crossref","unstructured":"Fathy, M. E., Tran, Q.-H., Zia, M. Z., Vernaza, P., & Chandraker, M. (2018). Hierarchical metric learning and matching for 2d and 3d geometric correspondences. In Proceedings of the European conference on computer vision (ECCV) (pp. 803\u2013819).","DOI":"10.1007\/978-3-030-01267-0_49"},{"key":"2090_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The Kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3354\u20133361). IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"3","key":"2090_CR18","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1109\/TRO.2019.2899783","volume":"35","author":"R Gomez-Ojeda","year":"2019","unstructured":"Gomez-Ojeda, R., Moreno, F.-A., Zuniga-No\u00ebl, D., Scaramuzza, D., & Gonzalez-Jimenez, J. (2019). Pl-slam: A stereo slam system through the combination of points and line segments. IEEE Transactions on Robotics, 35(3), 734\u2013746.","journal-title":"IEEE Transactions on Robotics"},{"key":"2090_CR19","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., & Li, H. (2019). Group-wise correlation stereo network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3273\u20133282).","DOI":"10.1109\/CVPR.2019.00339"},{"key":"2090_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2090_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2090_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2090_CR23","doi-asserted-by":"crossref","unstructured":"Hirschmuller, H. (2005). Accurate and efficient stereo processing by semi-global matching and mutual information. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905) (vol.\u00a02., pp. 807\u2013814). IEEE.","DOI":"10.1109\/CVPR.2005.56"},{"issue":"2","key":"2090_CR24","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller, H. (2007). Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 328\u2013341.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2090_CR25","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TPAMI.2012.156","volume":"35","author":"A Hosni","year":"2012","unstructured":"Hosni, A., Rhemann, C., Bleyer, M., Rother, C., & Gelautz, M. (2012). Fast cost-volume filtering for visual correspondence and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2), 504\u2013511.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR26","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., & Bry, A. (2017). End-to-end learning of geometry and context for deep stereo regression. In Proceedings of the IEEE international conference on computer vision (pp. 66\u201375).","DOI":"10.1109\/ICCV.2017.17"},{"key":"2090_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, P., Xiong, P., Cai, T., Yan, Z., Yang, L., Liu, J., Fan, H., & Liu, S. (2022). Practical stereo matching via cascaded recurrent network with adaptive correlation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16263\u201316272).","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"2090_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., & He, K. (2022). Exploring plain vision transformer backbones for object detection. In European conference on computer vision (pp. 280\u2013296). Berlin: Springer.","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"2090_CR29","doi-asserted-by":"crossref","unstructured":"Liang, Z., Feng, Y., Guo, Y., Liu, H., Chen, W., Qiao, L., Zhou, L., & Zhang, J. (2018). Learning for disparity estimation through feature constancy. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2811\u20132820).","DOI":"10.1109\/CVPR.2018.00297"},{"key":"2090_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"2090_CR31","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., & Deng, J. (2021). Raft-stereo: Multilevel recurrent field transforms for stereo matching. In 2021 International conference on 3D vision (3DV) (pp. 218\u2013227). IEEE.","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"2090_CR32","doi-asserted-by":"crossref","unstructured":"Liu, B., Yu, H., & Long, Y. (2022a). Local similarity pattern and cost self-reassembling for deep stereo matching networks. Proceedings of the AAAI conference on artificial intelligence, (vol. 36(no. 2), pp. 1647\u20131655).","DOI":"10.1609\/aaai.v36i2.20056"},{"key":"2090_CR33","doi-asserted-by":"crossref","unstructured":"Liu, B., Yu, H., & Qi, G. (2022b). Graftnet: Towards domain generalized stereo matching with a broad-spectrum and task-oriented feature. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13012\u201313021).","DOI":"10.1109\/CVPR52688.2022.01267"},{"key":"2090_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021), \u201cSwin transformer: Hierarchical vision transformer using shifted windows. In 2021 Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2090_CR35","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1007\/s11263-018-1082-6","volume":"126","author":"N Mayer","year":"2018","unstructured":"Mayer, N., Ilg, E., Fischer, P., Hazirbas, C., Cremers, D., Dosovitskiy, A., & Brox, T. (2018). What makes good synthetic training data for learning disparity and optical flow estimation? International Journal of Computer Vision, 126, 942\u2013960.","journal-title":"International Journal of Computer Vision"},{"key":"2090_CR36","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4040\u20134048).","DOI":"10.1109\/CVPR.2016.438"},{"key":"2090_CR37","doi-asserted-by":"crossref","unstructured":"Menze, M., & Geiger, A. (2015). Object scene flow for autonomous vehicles. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3061\u20133070).","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"2090_CR38","first-page":"66","volume":"6","author":"M Poggi","year":"2021","unstructured":"Poggi, M., Tonioni, A., Tosi, F., Mattoccia, S., & Di Stefano, L. (2021). Continual adaptation for deep stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 66.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"2090_CR39","first-page":"5314","volume":"44","author":"M Poggi","year":"2021","unstructured":"Poggi, M., Tosi, F., Batsos, K., Mordohai, P., & Mattoccia, S. (2021). On the synergies between machine learning and binocular stereo for depth estimation from images: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5314\u20135334.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR40","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., & Dosovitskiy, A. (2021). Do vision transformers see like convolutional neural networks? Advances in Neural Information Processing Systems, 34, 12116\u201312128.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"2090_CR41","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., & Koltun, V. (2020). Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3), 1623\u20131637.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR42","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Chen, G., Tang, Y., Zhu, Z., Huang, G., Zhou, J., & Lu, J. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18082\u201318091).","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2090_CR43","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., & Berg, A. C. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2090_CR44","doi-asserted-by":"crossref","unstructured":"Scharstein, D., Hirschm\u00fcller, H., Kitajima, Y., Krathwohl, G., Ne\u0161i\u0107, N., Wang, X., & Westling, P. (2014). High-resolution stereo datasets with subpixel-accurate ground truth. In German conference on pattern recognition (pp. 31\u201342). Berlin: Springer.","DOI":"10.1007\/978-3-319-11752-2_3"},{"issue":"1","key":"2090_CR45","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"Scharstein, D., & Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1), 7\u201342.","journal-title":"International Journal of Computer Vision"},{"key":"2090_CR46","doi-asserted-by":"crossref","unstructured":"Schops, T., Schonberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., & Geiger, A. (2017). A multi-view stereo benchmark with high-resolution images and multi-camera videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3260\u20133269).","DOI":"10.1109\/CVPR.2017.272"},{"key":"2090_CR47","doi-asserted-by":"crossref","unstructured":"Shaked, A., & Wolf, L. (2017). Improved stereo matching with constant highway networks and reflective confidence learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4641\u20134650).","DOI":"10.1109\/CVPR.2017.730"},{"key":"2090_CR48","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., & Rao, Z. (2021). Cfnet: Cascade and fused cost volume for robust stereo matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13906\u201313915).","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"2090_CR49","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., Song, X., Rao, Z., Zhou, D., & Zhang, L. (2022). Pcw-net: Pyramid combination and warping cost volume for stereo matching. In European conference on computer vision (pp. 280\u2013297). Berlin: Springer.","DOI":"10.1007\/978-3-031-19824-3_17"},{"key":"2090_CR50","doi-asserted-by":"crossref","unstructured":"Shi, X., Huang, Z., Li, D., Zhang, M., Cheung, K. C., See, S., Qin, H., Dai, J., & Li, H. (2023). Flowformer++: Masked cost volume autoencoding for pretraining optical flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1599\u20131610).","DOI":"10.1109\/CVPR52729.2023.00160"},{"key":"2090_CR51","doi-asserted-by":"crossref","unstructured":"Sivaraman, S., & Trivedi, M. M. (2013). A review of recent developments in vision-based vehicle detection. In 2013 IEEE intelligent vehicles symposium (IV) (pp. 310\u2013315). IEEE.","DOI":"10.1109\/IVS.2013.6629487"},{"key":"2090_CR52","first-page":"1","volume":"66","author":"X Song","year":"2022","unstructured":"Song, X., Yang, G., Zhu, X., Zhou, H., Ma, Y., Wang, Z., & Shi, J. (2022). Adastereo: An efficient domain-adaptive stereo matching approach. International Journal of Computer Vision, 66, 1\u201320.","journal-title":"International Journal of Computer Vision"},{"key":"2090_CR53","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of data in deep learning era. In Proceedings of the IEEE international conference on computer vision (pp. 843\u2013852).","DOI":"10.1109\/ICCV.2017.97"},{"key":"2090_CR54","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16 (402\u2013419). Berlin: Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"2090_CR55","doi-asserted-by":"crossref","unstructured":"Tonioni, A., Tosi, F., Poggi, M., Mattoccia, S., & Stefano, L.D. (2019). Real-time self-adaptive deep stereo. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 195\u2013204).","DOI":"10.1109\/CVPR.2019.00028"},{"key":"2090_CR56","doi-asserted-by":"crossref","unstructured":"Tosi, F., Tonioni, A., De\u00a0Gregorio, D., & Poggi, M. (2023). Nerf-supervised deep stereo. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 855\u2013866).","DOI":"10.1109\/CVPR52729.2023.00089"},{"key":"2090_CR57","doi-asserted-by":"crossref","unstructured":"Vasconcelos, C., Birodkar, V., & Dumoulin, V. (2022). Proper reuse of image classification features improves object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13628\u201313637).","DOI":"10.1109\/CVPR52688.2022.01326"},{"issue":"3","key":"2090_CR58","doi-asserted-by":"publisher","first-page":"4353","DOI":"10.1109\/LRA.2021.3068108","volume":"6","author":"H Wang","year":"2021","unstructured":"Wang, H., Fan, R., Cai, P., & Liu, M. (2021). Pvstereo: Pyramid voting module for end-to-end self-supervised stereo matching. IEEE Robotics and Automation Letters, 6(3), 4353\u20134360.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2090_CR59","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., & Li, L. (2021). Dense contrastive learning for self-supervised visual pre-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3024\u20133033).","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"2090_CR60","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2022). Simmim: A simple framework for masked image modeling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9653\u20139663).","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2090_CR61","doi-asserted-by":"crossref","unstructured":"Xu, G., Cheng, J., Guo, P., & Yang, X. (2022). Attention concatenation volume for accurate and efficient stereo matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12981\u201312990).","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"2090_CR62","doi-asserted-by":"crossref","unstructured":"Xu, G., Wang, X., Ding, X., & Yang, X. (2023). Iterative geometry encoding volume for stereo matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 21919\u201321928).","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"2090_CR63","first-page":"66","volume":"6","author":"G Xu","year":"2023","unstructured":"Xu, G., Wang, Y., Cheng, J., Tang, J., & Yang, X. (2023). Accurate and efficient stereo matching via attention concatenation volume. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 66.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2090_CR64","doi-asserted-by":"crossref","unstructured":"Xu, H., & Zhang, J. (2020). Aanet: Adaptive aggregation network for efficient stereo matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1959\u20131968).","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"2090_CR65","doi-asserted-by":"crossref","unstructured":"Yin, Z., Darrell, T., & Yu, F. (2019). Hierarchical discrete distribution decomposition for match density estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6044\u20136053).","DOI":"10.1109\/CVPR.2019.00620"},{"key":"2090_CR66","doi-asserted-by":"crossref","unstructured":"Zabih, R., & Woodfill, J. (1994). Non-parametric local transforms for computing visual correspondence. In European conference on computer vision (pp. 151\u2013158). Berlin: Springer.","DOI":"10.1007\/BFb0028345"},{"key":"2090_CR67","doi-asserted-by":"crossref","unstructured":"Zbontar, J., & LeCun, Y. (2015). Computing the stereo matching cost with a convolutional neural network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1592\u20131599).","DOI":"10.1109\/CVPR.2015.7298767"},{"issue":"1","key":"2090_CR68","first-page":"2287","volume":"17","author":"J Zbontar","year":"2016","unstructured":"Zbontar, J., & LeCun, Y. (2016). Stereo matching by training a convolutional neural network to compare image patches. Journal of Machine Learning Research, 17(1), 2287\u20132318.","journal-title":"Journal of Machine Learning Research"},{"key":"2090_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., & Torr, P.H. (2019). Ga-net: Guided aggregation net for end-to-end stereo matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 185\u2013194).","DOI":"10.1109\/CVPR.2019.00027"},{"key":"2090_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, F., Qi, X., Yang, R., Prisacariu, V., Wah, B., & Torr, P. (2020). Domain-invariant stereo matching networks. In European conference on computer vision (pp. 420\u2013439). Berlin: Springer.","DOI":"10.1007\/978-3-030-58536-5_25"},{"issue":"2","key":"2090_CR71","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1109\/TIP.2017.2752370","volume":"27","author":"F Zhang","year":"2017","unstructured":"Zhang, F., & Wah, B. W. (2017). Fundamental principles on learning new features for effective dense matching. IEEE Transactions on Image Processing, 27(2), 822\u2013836.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2090_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Bai, X., Wang, C., Huang, L., Chen, Y., Gu, L., Zhou, J., Harada, T., & Hancock, E.R. (2022). Revisiting domain generalized stereo matching networks from a feature consistency perspective. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13001\u201313011).","DOI":"10.1109\/CVPR52688.2022.01266"},{"key":"2090_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, Y., Bai, X., Yu, S., Yu, K., Li, Z., & Yang, K. (2020). Adaptive unimodal cost volume filtering for deep stereo matching. In Proceedings of the AAAI conference on artificial intelligence (vol. 34(no. 7), pp. 12926\u201312934).","DOI":"10.1609\/aaai.v34i07.6991"},{"key":"2090_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., & Hu, Q. (2021). Transfuse: Fusing transformers and cnns for medical image segmentation. In Medical image computing and computer assisted intervention\u2013MICCAI 2021: 4th international conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24 (pp. 14\u201324). Berlin: Springer.","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"2090_CR75","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, H., Zhang, Y., Chen, J., Yang, Y., & Zhao, Y. (2023). High-frequency stereo matching network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1327\u20131336).","DOI":"10.1109\/CVPR52729.2023.00134"},{"key":"2090_CR76","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H., & Zhang, L. (2021). Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6881\u20136890).","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2090_CR77","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection, arXiv preprint arXiv:2010.04159."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02090-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02090-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02090-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T06:18:31Z","timestamp":1728022711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02090-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":77,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["2090"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02090-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"10 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}