{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:50:35Z","timestamp":1774021835878,"version":"3.50.1"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3302200"],"award-info":[{"award-number":["2022YFC3302200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intelligent Logistics Interdisciplinary Team Project of BUPT"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Human matting refers to extracting human parts from natural images with high quality, including human detail information such as hair, glasses, hats, etc. This technology plays an essential role in image synthesis and visual effects in the film industry. When the green screen is not available, the existing human matting methods need the help of additional inputs (such as trimap, background image, etc.), or the model with high computational cost and complex network structure, which brings great difficulties to the application of human matting in practice. To alleviate such problems, we use a segmentation network as the foundation and use multiple branches to achieve human segmentation, contour detail extraction, and information fusion. We also propose a foreground probability map module, which uses the feature maps in the segmentation network to pre-estimate the foreground probabilities of each pixel and obtain Semantic Guided Matting Net. Under the condition that only a single image is needed as the input, the human matting task can be realized by making full use of the semantic information in the image. We validate our method on the P3M-10k dataset. Compared with the benchmark, our method has made significant improvements in various evaluation indicators.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae113","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T08:51:14Z","timestamp":1730710274000},"page":"322-330","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Guided Matting Net"],"prefix":"10.1093","volume":"68","author":[{"given":"Qing","family":"Song","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligence Vision Lab, Beijing University of Posts and Telecommunications , Beijing 100876 ,","place":["China"]}]},{"given":"Wenfeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligence Vision Lab, Beijing University of Posts and Telecommunications , Beijing 100876 ,","place":["China"]}]},{"given":"Donghan","family":"Yang","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligence Vision Lab, Beijing University of Posts and Telecommunications , Beijing 100876 ,","place":["China"]}]},{"given":"Mengjie","family":"Hu","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligence Vision Lab, Beijing University of Posts and Telecommunications , Beijing 100876 ,","place":["China"]}]},{"given":"Chun","family":"Liu","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligence Vision Lab, Beijing University of Posts and Telecommunications , Beijing 100876 ,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"2025031911065829400_ref1","first-page":"398","article-title":"Real-time fashion-guided clothing semantic parsing: A lightweight multi-scale inception neural network and benchmark","volume-title":"Proceedings of the 31st International Conference on Artificial Intelligence (AAAI)","author":"He","year":"2017"},{"key":"2025031911065829400_ref2","first-page":"8758","article-title":"Real-time high-resolution background matting","volume-title":"Proceedings of the 32nd International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":"2021"},{"key":"2025031911065829400_ref3","first-page":"2288","article-title":"Background matting: the world is your green screen","volume-title":"Proceedings of the 31st International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sengupta","year":"2020"},{"key":"2025031911065829400_ref4","doi-asserted-by":"publisher","first-page":"11450","DOI":"10.1609\/aaai.v34i07.6809","article-title":"Natural image matting via guided contextual attention","volume-title":"Proceedings of the 34th International Conference on Artificial Intelligence (AAAI)","author":"Li","year":"2020"},{"key":"2025031911065829400_ref5","first-page":"311","article-title":"Deep image matting","volume-title":"Proceedings of the 28th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu","year":"2017"},{"key":"2025031911065829400_ref6","first-page":"1","article-title":"Automatic trimap generation for image matting","volume-title":"Proceedings of the 1st International Conference on Signal and Information Processing (IConSIP)","author":"Gupta","year":"2016"},{"key":"2025031911065829400_ref7","first-page":"8560","article-title":"Boosting semantic human matting with coarse annotations","volume-title":"Proceedings of the 31st International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2020"},{"key":"2025031911065829400_ref8","first-page":"1154","article-title":"Mask guided matting via progressive refinement network","volume-title":"Proceedings of the 32nd International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yu","year":"2021"},{"key":"2025031911065829400_ref9","first-page":"13673","article-title":"Attention-guided hierarchical structure aggregation for image matting","volume-title":"Proceedings of the 31st International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qiao","year":"2020"},{"key":"2025031911065829400_ref10","first-page":"7461","article-title":"A late fusion cnn for digital matting","volume-title":"Proceedings of the 30th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang","year":"2019"},{"key":"2025031911065829400_ref11","article-title":"Is a green screen really necessary for real-time portrait matting?","author":"Ke","year":"2020"},{"key":"2025031911065829400_ref12","first-page":"3132","article-title":"Robust high-resolution video matting with temporal guidance","volume-title":"Proceedings of the 21st Winter Conference on Applications of Computer Vision (WACV)","author":"Lin","year":"2022"},{"key":"2025031911065829400_ref13","first-page":"8709","article-title":"Locality-aware inter-and intra-video reconstruction for self-supervised correspondence learning","volume-title":"Proceedings of the 33rd International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li","year":"2022"},{"key":"2025031911065829400_ref14","doi-asserted-by":"publisher","first-page":"3009","DOI":"10.1093\/comjnl\/bxae065","article-title":"Pornographic video detection based on semantic and image enhancement","volume":"67","author":"Zeng","year":"2024","journal-title":"Comput J"},{"key":"2025031911065829400_ref15","doi-asserted-by":"crossref","first-page":"3501","DOI":"10.1145\/3474085.3475512","article-title":"Privacy-preserving portrait matting","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Li","year":"2021"},{"key":"2025031911065829400_ref16","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.1109\/TPAMI.2021.3059968","article-title":"Image segmentation using deep learning: A survey","volume":"44","author":"Minaee","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025031911065829400_ref17","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1093\/comjnl\/bxab079","article-title":"Robust object detection and localization using semantic segmentation network","volume":"64","author":"Raghu Alfred","year":"2021","journal-title":"Comput J"},{"key":"2025031911065829400_ref18","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1093\/comjnl\/bxaa118","article-title":"Retrieving semantic image using shape descriptors and latent-dynamic conditional random fields","volume":"64","author":"Elmezain","year":"2021","journal-title":"Comput J"},{"key":"2025031911065829400_ref19","first-page":"228","article-title":"Designing effective inter-pixel information flow for natural image matting","volume-title":"Proceedings of the 28th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Aksoy","year":"2017"},{"key":"2025031911065829400_ref20","first-page":"2049","article-title":"A global sampling method for alpha matting","volume-title":"Proceedings of the 22st International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2011"},{"key":"2025031911065829400_ref21","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1109\/TPAMI.2013.18","article-title":"KNN matting","volume":"35","author":"Chen","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025031911065829400_ref22","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-319-46475-6_39","article-title":"Natural image matting using deep convolutional neural networks","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV)","author":"Cho","year":"2016"},{"key":"2025031911065829400_ref23","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-319-46448-0_6","article-title":"Deep automatic portrait matting","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV)","author":"Shen","year":"2016"},{"key":"2025031911065829400_ref24","first-page":"259","article-title":"AlphaGAN: generative adversarial networks for natural image matting","volume-title":"Proceedings of the 29th International Conference on British Machine Vision Conference (BMVC)","author":"Lutz","year":"2018"},{"key":"2025031911065829400_ref25","first-page":"3055","article-title":"Learning-based sampling for natural image matting","volume-title":"Proceedings of the 30th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tang","year":"2019"},{"key":"2025031911065829400_ref26","first-page":"4130","article-title":"Context-aware image matting for simultaneous foreground and alpha estimation","volume-title":"Proceedings of the 26th IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Hou","year":"2019"},{"key":"2025031911065829400_ref27","first-page":"3266","article-title":"Indices matter: learning to index for deep image matting","volume-title":"Proceedings of the 26th IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Lu","year":"2019"},{"key":"2025031911065829400_ref28","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/s11263-021-01541-0","article-title":"Bridging composite and real: towards end-to-end deep image matting","volume":"130","author":"Li","year":"2022","journal-title":"Int J Comput Vis"},{"key":"2025031911065829400_ref29","first-page":"7132","article-title":"Squeeze- and-excitation networks","volume-title":"Proceedings of the 29th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu","year":"2018"},{"key":"2025031911065829400_ref30","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1145\/3240508.3240610","article-title":"Semantic human matting","volume-title":"Proceedings of the 26th ACM International Conference on Multimedia","author":"Chen","year":"2018"},{"key":"2025031911065829400_ref31","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-031-19818-2_15","article-title":"TransMatting: Enhancing transparent objects matting with transformers","volume-title":"Proceedings of the 20th European Conference on Computer Vision (ECCV)","author":"Cai","year":"2022"},{"key":"2025031911065829400_ref32","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00986","article-title":"Adaptive human matting for dynamic videos","volume-title":"Proceedings of the 34th International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":"2023"},{"key":"2025031911065829400_ref33","article-title":"Salient image matting","author":"Deora","year":"2021"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/3\/322\/60385492\/bxae113.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/3\/322\/60385492\/bxae113.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T11:07:17Z","timestamp":1742382437000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/3\/322\/7874330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,11,4]]},"published-print":{"date-parts":[[2025,3,18]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae113","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2024,11,4]]}}}