{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:10:26Z","timestamp":1772824226768,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00371-024-03430-2","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:23:31Z","timestamp":1716920611000},"page":"7045-7055","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Depth-based adaptable image layer prediction using bidirectional depth semantic fusion"],"prefix":"10.1007","volume":"40","author":[{"given":"Jie","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwen","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lipai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaifeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,28]]},"reference":[{"key":"3430_CR1","doi-asserted-by":"crossref","unstructured":"Gupta, V., Raman, S.: Automatic trimap generation for image matting. In: IConSIP, pp. 1\u20135. IEEE (2016)","DOI":"10.1109\/ICONSIP.2016.7857477"},{"key":"3430_CR2","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"3430_CR3","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"3430_CR4","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3DV, pp. 239\u2013248 (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"3430_CR5","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Van Den\u00a0Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: CVPR, pp. 3194\u20133203 (2016)","DOI":"10.1109\/CVPR.2016.348"},{"key":"3430_CR6","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: CVPR, pp. 1925\u20131934 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"3430_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Cai, R., Li, Z., Zhao, X., Huang, K.: Locality-sensitive deconvolution networks with gated fusion for RGB-D indoor semantic segmentation. In: CVPR, pp. 3029\u20133037 (2017)","DOI":"10.1109\/CVPR.2017.161"},{"key":"3430_CR8","doi-asserted-by":"crossref","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: Acnet: attention based network to exploit complementary features for RGBD semantic segmentation. In: ICIP, pp. 1440\u20131444. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"3430_CR9","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., Li, J.: Salient object detection: a survey. Comput. Vis. Media 5, 117\u2013150 (2019)","journal-title":"Comput. Vis. Media"},{"key":"3430_CR10","first-page":"2313","volume":"30","author":"L-Z Chen","year":"2021","unstructured":"Chen, L.-Z., Lin, Z., Wang, Z., Yang, Y.-L., Cheng, M.-M.: Spatial information guided convolution for real-time RGBD semantic segmentation. IEEE TIP 30, 2313\u20132324 (2021)","journal-title":"IEEE TIP"},{"key":"3430_CR11","doi-asserted-by":"crossref","unstructured":"Chen, H., Li, Y.-F., Su, D.: M$$^3$$ net: multi-scale multi-path multi-modal fusion network and example application to RGB-D salient object detection. In: IROS, pp. 4911\u20134916. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206370"},{"key":"3430_CR12","doi-asserted-by":"crossref","unstructured":"Cong, R., Lei, J., Fu, H., Hou, J., Huang, Q., Kwong, S.: Going from RGB to RGBD saliency: a depth-guided transformation model. IEEE TCYB 50(8), 3627\u20133639 (2019)","DOI":"10.1109\/TCYB.2019.2932005"},{"key":"3430_CR13","first-page":"730","volume":"29","author":"W Chen","year":"2016","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. Adv. Neural Inf. Process. Systems 29, 730\u2013738 (2016)","journal-title":"Adv. Neural Inf. Process. Systems"},{"issue":"10","key":"3430_CR14","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.1109\/TPAMI.2019.2926728","volume":"42","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., Yang, J.: Joint task-recursive learning for RGB-D scene understanding. IEEE TPAMI 42(10), 2608\u20132623 (2020)","journal-title":"IEEE TPAMI"},{"key":"3430_CR15","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Sebe, N.: Pad-net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: CVPR, pp. 675\u2013684 (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"issue":"6","key":"3430_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356528","volume":"38","author":"S Niklaus","year":"2019","unstructured":"Niklaus, S., Mai, L., Yang, J., Liu, F.: 3d ken burns effect from a single image. ACM ToG 38(6), 1\u201315 (2019)","journal-title":"ACM ToG"},{"key":"3430_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, J., Wang, O., Lin, Z., Lu, H.: Sdc-depth: semantic divide-and-conquer network for monocular depth estimation. In: CVPR, pp. 538\u2013547 (2020)","DOI":"10.1109\/CVPR42600.2020.00062"},{"key":"3430_CR18","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.neucom.2021.01.126","volume":"440","author":"L He","year":"2021","unstructured":"He, L., Lu, J., Wang, G., Song, S., Zhou, J.: Sosd-net: joint semantic object segmentation and depth estimation from monocular images. Neurocomputing 440, 251\u2013263 (2021)","journal-title":"Neurocomputing"},{"issue":"8","key":"3430_CR19","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.P.: Bagfn: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"3430_CR20","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2021","unstructured":"Li, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Inform. 18(1), 163\u2013173 (2021)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"3430_CR21","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"N Jiang","year":"2022","unstructured":"Jiang, N., Sheng, B., Li, P., Lee, T.-Y.: Photohelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multimed. 25, 2226\u20132238 (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3144890","journal-title":"IEEE Trans. Multimed."},{"issue":"11","key":"3430_CR22","doi-asserted-by":"publisher","first-page":"13489","DOI":"10.1109\/TPAMI.2023.3293885","volume":"45","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: Mngnas: distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13489\u201313508 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3293885","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"3430_CR23","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"B Sheng","year":"2021","unstructured":"Sheng, B., Li, P., Ali, R., Chen, C.P.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662\u20136675 (2021)","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"3430_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2988229","volume":"36","author":"J Tan","year":"2016","unstructured":"Tan, J., Lien, J.-M., Gingold, Y.: Decomposing images into layers via RGB-space geometry. ACM ToG 36(1), 1\u201314 (2016)","journal-title":"ACM ToG"},{"key":"3430_CR25","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1111\/cgf.13577","volume":"37","author":"Y Koyama","year":"2018","unstructured":"Koyama, Y., Goto, M.: Decomposing images into layers with advanced color blending. Comput. Graph. Forum 37, 397\u2013407 (2018)","journal-title":"Comput. Graph. Forum"},{"issue":"8","key":"3430_CR26","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1109\/TPAMI.2014.2377712","volume":"37","author":"JT Barron","year":"2014","unstructured":"Barron, J.T., Malik, J.: Shape, illumination, and reflectance from shading. IEEE TPAMI 37(8), 1670\u20131687 (2014)","journal-title":"IEEE TPAMI"},{"key":"3430_CR27","doi-asserted-by":"crossref","unstructured":"Shen, L., Tan, P., Lin, S.: Intrinsic image decomposition with non-local texture cues. In: 2008 CVPR, pp. 1\u20137. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587660"},{"issue":"6","key":"3430_CR28","first-page":"753","volume":"25","author":"G Han","year":"2018","unstructured":"Han, G., Xie, X., Lai, J., Zheng, W.-S.: Learning an intrinsic image decomposer using synthesized RGB-D dataset. IEEE SPL 25(6), 753\u2013757 (2018)","journal-title":"IEEE SPL"},{"key":"3430_CR29","doi-asserted-by":"crossref","unstructured":"Carroll, R., Ramamoorthi, R., Agrawala, M.: Illumination decomposition for material recoloring with consistent interreflections. In: ACM SIGGRAPH 2011 Papers, pp. 1\u201310 (2011)","DOI":"10.1145\/1964921.1964938"},{"key":"3430_CR30","doi-asserted-by":"crossref","unstructured":"Monnier, T., Vincent, E., Ponce, J., Aubry, M.: Unsupervised layered image decomposition into object prototypes. In: ICCV, pp. 8640\u20138650 (2021)","DOI":"10.1109\/ICCV48922.2021.00852"},{"key":"3430_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"issue":"1","key":"3430_CR32","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3430_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"3430_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3430_CR35","doi-asserted-by":"crossref","unstructured":"Jadon, S.: A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1\u20137. IEEE (2020)","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"3430_CR36","doi-asserted-by":"crossref","unstructured":"Gao, W., Zhang, X., Yang, L., Liu, H.: An improved sobel edge detection. In: 2010 3rd International Conference on Computer Science and Information Technology, vol. 5, pp. 67\u201371. IEEE (2010)","DOI":"10.1109\/ICCSIT.2010.5563693"},{"key":"3430_CR37","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV, vol. 7576, pp. 746\u2013760 (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"3430_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., Yang, J.: Joint task-recursive learning for semantic segmentation and depth estimation. In: ECCV, pp. 235\u2013251 (2018)","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"3430_CR39","doi-asserted-by":"crossref","unstructured":"Nekrasov, V., Dharmasiri, T., Spek, A., Drummond, T., Shen, C., Reid, I.: Real-time joint semantic segmentation and depth estimation using asymmetric annotations. In: ICRA, pp. 7101\u20137107. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794220"},{"issue":"8","key":"3430_CR40","doi-asserted-by":"publisher","first-page":"1795","DOI":"10.3390\/s19081795","volume":"19","author":"X Lin","year":"2019","unstructured":"Lin, X., S\u00e1nchez-Escobedo, D., Casas, J.R., Pard\u00e0s, M.: Depth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network. Sensors 19(8), 1795 (2019)","journal-title":"Sensors"},{"key":"3430_CR41","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Pirsiavash, H., Ko\u0161eck\u00e1, J.: Joint semantic segmentation and depth estimation with deep convolutional networks. In: 3DV, pp. 611\u2013619. IEEE (2016)","DOI":"10.1109\/3DV.2016.69"},{"key":"3430_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102877","volume":"191","author":"T Koch","year":"2020","unstructured":"Koch, T., Liebel, L., K\u00f6rner, M., Fraundorfer, F.: Comparison of monocular depth estimation methods using geometrically relevant metrics on the IBims-1 dataset. Comput. Vis. Image Underst. 191, 102877 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"3430_CR43","doi-asserted-by":"crossref","unstructured":"Chinchor, N., Sundheim, B.M.: Muc-5 evaluation metrics. In: 5th Message Understanding Conference (MUC-5): Proceedings of a Conference Held in Baltimore, Maryland (1993)","DOI":"10.3115\/1072017.1072026"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03430-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03430-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03430-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:36:14Z","timestamp":1732113374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03430-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,28]]},"references-count":43,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["3430"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03430-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,28]]},"assertion":[{"value":"22 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2024","order":2,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}