{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T13:46:10Z","timestamp":1781271970194,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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":[[2025,12]]},"DOI":"10.1007\/s00371-025-04180-5","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T12:35:38Z","timestamp":1758026138000},"page":"12679-12690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SAMirror: enhancing mirror detection via integrated visual-depth cues in segment anything model"],"prefix":"10.1007","volume":"41","author":[{"given":"Qiushi","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengmeng","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jixue","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"issue":"4","key":"4180_CR1","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4180_CR2","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation. arXiv preprint (2021) arXiv:2112.10764"},{"key":"4180_CR3","doi-asserted-by":"crossref","unstructured":"DelPozo, A., Savarese, S.: Detecting specular surfaces on natural images. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383215"},{"key":"4180_CR4","doi-asserted-by":"crossref","unstructured":"Guan, H., Lin, J., Lau, R.W.: Learning semantic associations for mirror detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5941\u20135950 (2022)","DOI":"10.1109\/CVPR52688.2022.00585"},{"issue":"7","key":"4180_CR5","doi-asserted-by":"publisher","first-page":"6238","DOI":"10.1109\/TCSVT.2024.3358415","volume":"34","author":"D Guo","year":"2024","unstructured":"Guo, D., Li, K., Hu, B., Zhang, Y., Wang, M.: Benchmarking micro-action recognition: dataset, method, and application. IEEE Trans. Circuits Syst. Video Technol. 34(7), 6238\u20136252 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4180_CR6","unstructured":"Han, D., Zhang, C., Qiao, Y., Qamar, M., Jung, Y., Lee, S., Bae, S.H., Hong, C.S.: Segment anything model (sam) meets glass: Mirror and transparent objects cannot be easily detected. arXiv preprint (2023) arXiv:2305.00278"},{"key":"4180_CR7","doi-asserted-by":"crossref","unstructured":"He, R., Lin, J., Lau, R.W.: Efficient mirror detection via multi-level heterogeneous learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 37, pp. 790\u2013798 (2023)","DOI":"10.1609\/aaai.v37i1.25157"},{"key":"4180_CR8","doi-asserted-by":"crossref","unstructured":"Huang, D., Xiong, X., Ma, J., Li, J., Jie, Z., Ma, L., Li, G.: Alignsam: Aligning segment anything model to open context via reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3205\u20133215 (2024)","DOI":"10.1109\/CVPR52733.2024.00309"},{"key":"4180_CR9","unstructured":"Jie, L.: When sam2 meets video shadow and mirror detection. arXiv preprint (2024) arXiv:2412.19293"},{"issue":"1","key":"4180_CR10","doi-asserted-by":"publisher","first-page":"e2197","DOI":"10.1002\/cav.2197","volume":"35","author":"DM Kim","year":"2024","unstructured":"Kim, D.M., Ahn, J., Kim, S., Lee, J., Kim, M., Han, J.: Real-time reconstruction of pipes using rgb-d cameras. Comput. Animat. Virtual Worlds 35(1), e2197 (2024)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"4180_CR11","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"5","key":"4180_CR12","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.vrih.2022.08.005","volume":"4","author":"C Li","year":"2022","unstructured":"Li, C., Yi, R., Ali, S.G., Ma, L., Wu, E., Wang, J., Mao, L., Sheng, B.: Radepthnet: Reflectance-aware monocular depth estimation. Virtual Reality & Intell. Hardware 4(5), 418\u2013431 (2022)","journal-title":"Virtual Reality & Intell. Hardware"},{"issue":"10","key":"4180_CR13","doi-asserted-by":"publisher","first-page":"6797","DOI":"10.1007\/s00371-024-03332-3","volume":"40","author":"S Li","year":"2024","unstructured":"Li, S., Lyu, C., Xia, B., Chen, Z., Zhang, L.: Tamdepth: self-supervised monocular depth estimation with transformer and adapter modulation. Vis. Comput. 40(10), 6797\u20136808 (2024)","journal-title":"Vis. Comput."},{"key":"4180_CR14","doi-asserted-by":"crossref","unstructured":"Li, W., Xiong, X., Xia, P., Ju, L., Ge, Z.: Tp-drseg: improving diabetic retinopathy lesion segmentation with explicit text-prompts assisted sam. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 743\u2013753. Springer (2024)","DOI":"10.1007\/978-3-031-72111-3_70"},{"key":"4180_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Tan, X., Lau, R.W.: Learning to detect mirrors from videos via dual correspondences. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9109\u20139118 (2023)","DOI":"10.1109\/CVPR52729.2023.00879"},{"key":"4180_CR16","doi-asserted-by":"crossref","unstructured":"Lin, J., Tan, X., Lau, R.W.: Learning to detect mirrors from videos via dual correspondences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9109\u20139118 (2023)","DOI":"10.1109\/CVPR52729.2023.00879"},{"key":"4180_CR17","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, G., Lau, R.W.: Progressive mirror detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3697\u20133705 (2020)","DOI":"10.1109\/CVPR42600.2020.00375"},{"key":"4180_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"4180_CR19","doi-asserted-by":"crossref","unstructured":"Liu, L., Prost, J., Zhu, L., Papadakis, N., Li\u00f2, P., Sch\u00f6nlieb, C.B., Aviles-Rivero, A.I.: Scotch and soda: A transformer video shadow detection framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10449\u201310458 (2023)","DOI":"10.1109\/CVPR52729.2023.01007"},{"key":"4180_CR20","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4180_CR21","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15, 654 (2024)","journal-title":"Nat. Commun."},{"key":"4180_CR22","doi-asserted-by":"crossref","unstructured":"Madeira, T., Oliveira, M., Dias, P.: Reflection-aware 3d mirror segmentation and pose estimation. The Visual Computer pp. 1\u201310 (2024)","DOI":"10.1007\/s00371-024-03704-9"},{"key":"4180_CR23","doi-asserted-by":"crossref","unstructured":"Mei, H., Dong, B., Dong, W., Peers, P., Yang, X., Zhang, Q., Wei, X.: Depth-aware mirror segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3044\u20133053 (2021)","DOI":"10.1109\/CVPR46437.2021.00306"},{"issue":"3","key":"4180_CR24","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1109\/TCSVT.2021.3069848","volume":"32","author":"H Mei","year":"2021","unstructured":"Mei, H., Liu, Y., Wei, Z., Zhou, D., Wei, X., Zhang, Q., Yang, X.: Exploring dense context for salient object detection. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1378\u20131389 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4180_CR25","unstructured":"Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., Gustafson, L., et\u00a0al.: Sam 2: Segment anything in images and videos. arXiv preprint (2024) arXiv:2408.00714"},{"key":"4180_CR26","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., Dean, J.: Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In: International Conference on Learning Representations (2017)"},{"issue":"4","key":"4180_CR27","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1109\/TCSVT.2019.2901629","volume":"30","author":"B Sheng","year":"2019","unstructured":"Sheng, B., Li, P., Fang, X., Tan, P., Wu, E.: Depth-aware motion deblurring using loopy belief propagation. IEEE Trans. Circuits Syst. Video Technol. 30(4), 955\u2013969 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"4180_CR28","first-page":"3492","volume":"45","author":"X Tan","year":"2022","unstructured":"Tan, X., Lin, J., Xu, K., Chen, P., Ma, L., Lau, R.W.: Mirror detection with the visual chirality cue. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3492\u20133504 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4180_CR29","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., Huang, Q.: F$$^3$$net: fusion, feedback and focus for salient object detection. In: AAAI, pp. 12321\u201312328 (2020)","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"4180_CR30","unstructured":"Wu, J., Ji, W., Liu, Y., Fu, H., Xu, M., Xu, Y., Jin, Y.: Medical sam adapter: Adapting segment anything model for medical image segmentation (2023)"},{"key":"4180_CR31","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: Simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4180_CR32","doi-asserted-by":"crossref","unstructured":"Xie, Z., Wang, S., Yu, Q., Tan, X., Xie, Y.: Csfwinformer: Cross-space-frequency window transformer for mirror detection. IEEE Transactions on Image Processing (2024)","DOI":"10.1109\/TIP.2024.3372468"},{"key":"4180_CR33","doi-asserted-by":"crossref","unstructured":"Xing, Z., Liu, L., Yang, Y., Wang, H., Ye, T., Chen, S., Li, W., Liu, G., Zhu, L.: Detect any mirrors: Boosting learning reliability on large-scale unlabeled data with an iterative data engine. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.02372"},{"key":"4180_CR34","unstructured":"Xing, Z., Liu, L., Ye, T., Chen, S., Yang, Y., Liu, G., Xu, X., Zhu, L.: Farther than mirror: Explore pattern-compensated depth of mirror with temporal changes for video mirror detection"},{"key":"4180_CR35","doi-asserted-by":"crossref","unstructured":"Xiong, X., Wang, C., Li, W., Li, G.: Mammo-sam: Adapting foundation segment anything model for automatic breast mass segmentation in whole mammograms. In: International Workshop on Machine Learning in Medical Imaging, pp. 176\u2013185. Springer (2023)","DOI":"10.1007\/978-3-031-45673-2_18"},{"key":"4180_CR36","unstructured":"Xiong, X., Wu, Z., Tan, S., Li, W., Tang, F., Chen, Y., Li, S., Ma, J., Li, G.: Sam2-unet: Segment anything 2 makes strong encoder for natural and medical image segmentation. arXiv preprint (2024) arXiv:2408.08870"},{"key":"4180_CR37","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Varadarajan, B., Wu, L., Xiang, X., Xiao, F., Zhu, C., Dai, X., Wang, D., Sun, F., Iandola, F., et\u00a0al.: Efficientsam: Leveraged masked image pretraining for efficient segment anything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16111\u201316121 (2024)","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"4180_CR38","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., Zhao, H.: Depth anything v2. In: Advances in Neural Information Processing Systems, vol. 37, pp. 21875\u201321911. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-0688"},{"key":"4180_CR39","doi-asserted-by":"crossref","unstructured":"Yang, X., Mei, H., Xu, K., Wei, X., Yin, B., Lau, R.W.: Where is my mirror? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8809\u20138818 (2019)","DOI":"10.1109\/ICCV.2019.00890"},{"issue":"1","key":"4180_CR40","doi-asserted-by":"publisher","first-page":"e2201","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., Zhu, M., You, L., Yang, X., Zhang, J., Zhao, H., Zeng, D.: Tmsdnet: Transformer with multi-scale dense network for single and multi-view 3d reconstruction. Comput. Animat. Virtual Worlds 35(1), e2201 (2024)","journal-title":"Comput. Animat. Virtual Worlds"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04180-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04180-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04180-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:16:18Z","timestamp":1763644578000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04180-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":40,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4180"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04180-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"11 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}