{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:37:06Z","timestamp":1779291426474,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11263-021-01545-w","type":"journal-article","created":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T12:02:41Z","timestamp":1641297761000},"page":"267-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["CODON: On Orchestrating Cross-Domain Attentions for Depth Super-Resolution"],"prefix":"10.1007","volume":"130","author":[{"given":"Yuxiang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,4]]},"reference":[{"issue":"10","key":"1545_CR1","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1007\/s11263-019-01200-5","volume":"127","author":"A Buades","year":"2019","unstructured":"Buades, A., Duran, J., & Navarro, J. (2019). Motion-compensated spatio-temporal filtering for multi-image and multimodal super-resolution. International Journal of Computer Vision, 127(10), 1474\u20131500.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR2","doi-asserted-by":"crossref","unstructured":"Butler, D. J., Wulff, J., Stanley, G. B., & Black, M. J. (2012). A naturalistic open source movie for optical flow evaluation. In European conference on computer vision (pp. 611\u2013625).","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"1545_CR3","unstructured":"Diebel, J., & Thrun, S. (2006). An application of Markov random fields to range sensing. In Proceedings of the international conference on neural information processing systems (pp. 291\u2013298)."},{"issue":"2","key":"1545_CR4","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 295\u2013307.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1545_CR5","doi-asserted-by":"crossref","unstructured":"Ferstl, D., Reinbacher, C., Ranftl, R., R\u00fcther, M., & Bischof, H. (2013). Image guided depth upsampling using anisotropic total generalized variation. In Proceedings of the IEEE international conference on computer vision (pp. 993\u20131000).","DOI":"10.1109\/ICCV.2013.127"},{"key":"1545_CR6","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., & Ponce, J. (2015). Robust image filtering using joint static and dynamic guidance. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4823\u20134831).","DOI":"10.1109\/CVPR.2015.7299115"},{"issue":"6","key":"1545_CR7","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1109\/TPAMI.2012.213","volume":"35","author":"K He","year":"2012","unstructured":"He, K., Sun, J., & Tang, X. (2012). Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(6), 1397\u20131409.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1545_CR8","doi-asserted-by":"crossref","unstructured":"Hirschmuller, H., & Scharstein, D. (2007). Evaluation of cost functions for stereo matching. In 2007 IEEE conference on computer vision and pattern recognition (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383248"},{"key":"1545_CR9","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1545_CR10","doi-asserted-by":"crossref","unstructured":"Hui, T. W., Loy, C. C., & Tang, X. (2016). Depth map super-resolution by deep multi-scale guidance. In European conference on computer vision (pp. 353\u2013369).","DOI":"10.1007\/978-3-319-46487-9_22"},{"key":"1545_CR11","doi-asserted-by":"crossref","unstructured":"Kiechle, M., Hawe, S., & Kleinsteuber, M. (2013). A joint intensity and depth co-sparse analysis model for depth map super-resolution. In Proceedings of the IEEE international conference on computer vision (pp. 1545\u20131552).","DOI":"10.1109\/ICCV.2013.195"},{"key":"1545_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Kwon\u00a0Lee, J., & Mu\u00a0Lee, K. (2016a). Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1646\u20131654).","DOI":"10.1109\/CVPR.2016.182"},{"key":"1545_CR13","doi-asserted-by":"crossref","unstructured":"Kim, J., Kwon\u00a0Lee, J., & Mu\u00a0Lee, K. (2016b). Deeply-recursive convolutional network for image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1637\u20131645).","DOI":"10.1109\/CVPR.2016.181"},{"key":"1545_CR14","unstructured":"Kwon, H., Tai, Y. W., & Lin, S. (2015). Data-driven depth map refinement via multi-scale sparse representation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 159\u2013167)."},{"issue":"11","key":"1545_CR15","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"1545_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Fang, F., Mei, K., & Zhang, G. (2018). Multi-scale residual network for image super-resolution. In Proceedings of the European conference on computer vision (ECCV) (pp. 517\u2013532).","DOI":"10.1007\/978-3-030-01237-3_32"},{"key":"1545_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, J. B., Ahuja, N., & Yang, M. H. (2016). Deep joint image filtering. In European conference on computer vision (pp. 154\u2013169).","DOI":"10.1007\/978-3-319-46493-0_10"},{"key":"1545_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Xue, T., Sun, L., & Liu, J. (2012). Joint example-based depth map super-resolution. In 2012 IEEE international conference on multimedia and expo (pp. 152\u2013157).","DOI":"10.1109\/ICME.2012.30"},{"key":"1545_CR19","unstructured":"Lu, J., & Forsyth, D. (2015). Sparse depth super resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2245\u20132253)."},{"key":"1545_CR20","doi-asserted-by":"crossref","unstructured":"Lutio, R. D., D\u2019Aronco, S., Wegner, J. D., & Schindler, K. (2019). Guided super-resolution as pixel-to-pixel transformation. In Proceedings of the IEEE international conference on computer vision (pp. 8829\u20138837).","DOI":"10.1109\/ICCV.2019.00892"},{"key":"1545_CR21","unstructured":"Martull, S., Peris, M., & Fukui, K. (2012). Realistic CG stereo image dataset with ground truth disparity maps. In ICPR workshop TrakMark2012 (Vol. 111, pp. 117\u2013118)."},{"key":"1545_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.imavis.2019.03.001","volume":"85","author":"HT Mustafa","year":"2019","unstructured":"Mustafa, H. T., Yang, J., & Zareapoor, M. (2019). Multi-scale convolutional neural network for multi-focus image fusion. Image and Vision Computing, 85, 26\u201335.","journal-title":"Image and Vision Computing"},{"key":"1545_CR23","unstructured":"Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10) (pp. 807\u2013814)."},{"key":"1545_CR24","doi-asserted-by":"crossref","unstructured":"Pei, Z., Cao, Z., Long, M., & Wang, J. (2018). Multi-adversarial domain adaptation. In Proceedings of the AAAI conference on artificial intelligence (pp. 3934\u20133941).","DOI":"10.1609\/aaai.v32i1.11767"},{"key":"1545_CR25","doi-asserted-by":"crossref","unstructured":"Qi, C. R., Liu, W., Wu, C., Su, H., & Guibas, L. J. (2018). Frustum pointnets for 3D object detection from RGB-D data. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 918\u2013927).","DOI":"10.1109\/CVPR.2018.00102"},{"key":"1545_CR26","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).","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"1545_CR27","doi-asserted-by":"crossref","unstructured":"Scharstein, D., & Pal, C. (2007). Learning conditional random fields for stereo. In 2007 IEEE conference on computer vision and pattern recognition (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383191"},{"issue":"1\u20133","key":"1545_CR28","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\u20133), 7\u201342.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR29","doi-asserted-by":"crossref","unstructured":"Scharstein, D., & Szeliski, R. (2003). High-accuracy stereo depth maps using structured light. In 2003 IEEE computer society conference on computer vision and pattern recognition, 2003. Proceedings (Vol.\u00a01, p. I).","DOI":"10.1109\/CVPR.2003.1211354"},{"key":"1545_CR30","doi-asserted-by":"crossref","unstructured":"Shen, X., Zhou, C., Xu, L., & Jia, J. (2015). Mutual-structure for joint filtering. In Proceedings of the IEEE international conference on computer vision (pp. 3406\u20133414).","DOI":"10.1109\/ICCV.2015.389"},{"key":"1545_CR31","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In European conference on computer vision (pp. 746\u2013760). Springer.","DOI":"10.1007\/978-3-642-33715-4_54"},{"issue":"11","key":"1545_CR32","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1007\/s11263-018-1081-7","volume":"126","author":"JS Supan\u010di\u010d","year":"2018","unstructured":"Supan\u010di\u010d, J. S., Rogez, G., Yang, Y., Shotton, J., & Ramanan, D. (2018). Depth-based hand pose estimation: Methods, data, and challenges. International Journal of Computer Vision, 126(11), 1180\u20131198.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"1545_CR34","doi-asserted-by":"crossref","unstructured":"Tai, Y., Yang, J., & Liu, X. (2017). Image super-resolution via deep recursive residual network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3147\u20133155).","DOI":"10.1109\/CVPR.2017.298"},{"key":"1545_CR35","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7167\u20137176).","DOI":"10.1109\/CVPR.2017.316"},{"key":"1545_CR36","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, D., Zhu, Y., Mart\u00edn-Mart\u00edn, R., Lu, C., Fei-Fei, L., & Savarese, S. (2019). Densefusion: 6D object pose estimation by iterative dense fusion. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3343\u20133352).","DOI":"10.1109\/CVPR.2019.00346"},{"key":"1545_CR37","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017). Residual attention network for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3156\u20133164).","DOI":"10.1109\/CVPR.2017.683"},{"key":"1545_CR38","doi-asserted-by":"crossref","unstructured":"Wei, M., Kang, Y., Song, W., & Cao, Y. (2018). Crowd distribution estimation with multi-scale recursive convolutional neural network. In International conference on multimedia modeling (pp. 142\u2013153). Springer.","DOI":"10.1007\/978-3-319-73603-7_12"},{"issue":"2","key":"1545_CR39","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TIP.2018.2874285","volume":"28","author":"Y Wen","year":"2019","unstructured":"Wen, Y., Sheng, B., Li, P., Lin, W., & Feng, D. D. (2019). Deep color guided coarse-to-fine convolutional network cascade for depth image super-resolution. IEEE Transactions on Image Processing, 28(2), 994\u20131006.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1545_CR40","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., & So\u00a0Kweon, I. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1545_CR41","unstructured":"Yue, K., Sun, M., Yuan,Y., Zhou, F., Ding, E., & Xu, F. (2018). Compact generalized non-local network. In Proceedings of the 32nd international conference on neural information processing systems (pp. 6511\u20136520)."},{"key":"1545_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zuo, W., & Zhang, L. (2018a). Learning a single convolutional super-resolution network for multiple degradations. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3262\u20133271).","DOI":"10.1109\/CVPR.2018.00344"},{"key":"1545_CR43","first-page":"1","volume":"128","author":"L Zhang","year":"2019","unstructured":"Zhang, L., Wang, P., Shen, C., Liu, L., Wei, W., Zhang, Y., & van den Hengel, A. (2019). Adaptive importance learning for improving lightweight image super-resolution network. International Journal of Computer Vision, 128, 1\u201321.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-019-01215-y","volume":"128","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Dong, H., Hu, Z., Lai, W. S., Wang, F., & Yang, M. H. (2020). Gated fusion network for degraded image super resolution. International Journal of Computer Vision, 128, 1\u201323.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018b). Image super-resolution using very deep residual channel attention networks. In Proceedings of the European conference on computer vision (ECCV) (pp. 286\u2013301).","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"1545_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018c). Residual dense network for image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2472\u20132481).","DOI":"10.1109\/CVPR.2018.00262"},{"key":"1545_CR47","first-page":"1","volume":"128","author":"H Zhou","year":"2019","unstructured":"Zhou, H., Ummenhofer, B., & Brox, T. (2019). Deeptam: Deep tracking and mapping with convolutional neural networks. International Journal of Computer Vision, 128, 1\u201314.","journal-title":"International Journal of Computer Vision"},{"key":"1545_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, W., Li, X., & Reynolds, D. (2017). Guided deep network for depth map super-resolution: How much can color help? In 2017 IEEE International conference on acoustics, speech and signal processing (ICASSP) (pp. 1457\u20131461).","DOI":"10.1109\/ICASSP.2017.7952398"},{"key":"1545_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhang, J., Cao, Y., & Wang, Z. (2017). Image guided depth enhancement via deep fusion and local linear regularizaron. In Proceedings of the IEEE international conference on image processing (pp. 4068\u20134072). IEEE.","DOI":"10.1109\/ICIP.2017.8297047"},{"issue":"2","key":"1545_CR50","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s11263-018-1133-z","volume":"127","author":"C Zou","year":"2019","unstructured":"Zou, C., Guo, R., Li, Z., & Hoiem, D. (2019). Complete 3D scene parsing from an RGBD image. International Journal of Computer Vision, 127(2), 143\u2013162.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01545-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01545-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01545-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T20:00:01Z","timestamp":1674331201000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01545-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,4]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1545"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01545-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,4]]},"assertion":[{"value":"8 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}