{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:07:03Z","timestamp":1767773223650,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61801159","61571174"],"award-info":[{"award-number":["61801159","61571174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In the end-to-end image generation task, the spatial domain of pixel space cannot explicitly separate the low-frequency general information such as texture and color from the high-frequency detail information such as structure and identity. The loss function calculated in the spatial domain fails to effectively constrain the maintenance of detail information, and the generated image quality is insufficient. In this paper, a wavelet domain image generation (WDIG) framework is proposed to preserve the frequency information of images, in which the loss functions are constructed in the pixel space and wavelet space. In the pixel space, the low-frequency and high-frequency characteristic information of the signal are obtained by setting the appropriate Gaussian kernel and adopting the Gaussian fuzzy method. The loss function of <jats:inline-formula><jats:alternatives><jats:tex-math>$$\\ell_{1}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mi>\u2113<\/mml:mi>\n                    <mml:mn>1<\/mml:mn>\n                  <\/mml:msub>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> norm spatial domain is constructed for the low-frequency and high-frequency characteristic information. In the wavelet space, the corresponding channel sub-band coefficients are obtained by wavelet transform, and the image is explicitly separated into high-frequency information and low-frequency information. The <jats:inline-formula><jats:alternatives><jats:tex-math>$$\\ell_{1}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mi>\u2113<\/mml:mi>\n                    <mml:mn>1<\/mml:mn>\n                  <\/mml:msub>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> norm frequency domain loss function is constructed respectively for the sub-band coefficients. The WDIG can constrain model training more accurately and optimize model more precisely, so as to better maintain the details and quality of generated image. The WDIG framework is evaluated in the image generation applications including style transfer, image translation and Generative Adversarial Nets (GAN) Inversion. Experimental results show that the WDIG framework can effectively retain the details of images and generate more realistic images, and improve the image quality of the above applications in image generation.<\/jats:p>","DOI":"10.1186\/s13634-023-01035-w","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T11:01:49Z","timestamp":1687172509000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["WDIG: a wavelet domain image generation framework based on frequency domain optimization"],"prefix":"10.1186","volume":"2023","author":[{"given":"Qing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiumei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junmei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1875-468X","authenticated-orcid":false,"given":"Huang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,19]]},"reference":[{"key":"1035_CR1","first-page":"142","volume":"4","author":"CE Shannon","year":"1959","unstructured":"C.E. Shannon, Coding theorems for a discrete source with a fidelity criterion. IRE Natl. Convent. Rec. 4, 142\u2013163 (1959)","journal-title":"IRE Natl. Convent. Rec."},{"doi-asserted-by":"publisher","unstructured":"Zhou K, Yang Y X, Hospedales T, et al. Deep Domain-Adversarial Image Generation for Domain Generalisation, in Proceedings of the AAAI Conference on Artificial Intelligence (2020), pp. 13025\u201313032. https:\/\/doi.org\/10.1609\/aaai.v34i07.7003.","key":"1035_CR2","DOI":"10.1609\/aaai.v34i07.7003"},{"issue":"5","key":"1035_CR3","doi-asserted-by":"publisher","first-page":"3681","DOI":"10.1109\/JIOT.2020.2967788","volume":"7","author":"X Jiang","year":"2020","unstructured":"X. Jiang, F.R. Yu, T. Song et al., Blockchain-enabled cross-domain object detection for autonomous driving: a model sharing approach. IEEE Internet Things J. 7(5), 3681\u20133692 (2020)","journal-title":"IEEE Internet Things J."},{"doi-asserted-by":"publisher","unstructured":"K. Xu, M. Qin, F. Sun, et al. Learning in the frequency domain, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Seattle, WA, 2020), pp. 1740\u20131749. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00181.","key":"1035_CR4","DOI":"10.1109\/CVPR42600.2020.00181"},{"doi-asserted-by":"publisher","unstructured":"L. Jiang, B. Dai, W. Wu, et al. Focal frequency loss for image reconstruction and synthesis, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Montreal Canada, 2021), pp. 13919\u201313929. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01366.","key":"1035_CR5","DOI":"10.1109\/ICCV48922.2021.01366"},{"doi-asserted-by":"publisher","unstructured":"W. Xie, D. Song, C. Xu, et al. Learning frequency-aware dynamic network for efficient super-resolution, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Montreal, Canada, 2021), pp. 4308\u20134317. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00427.","key":"1035_CR6","DOI":"10.1109\/ICCV48922.2021.00427"},{"doi-asserted-by":"publisher","unstructured":"M. Cai, H. Zhang, H. Huang, et al. Frequency domain image translation: more photo-realistic, better identity-preserving, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Montreal, Canada, 2021), pp. 13930\u201313940. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01367.","key":"1035_CR7","DOI":"10.1109\/ICCV48922.2021.01367"},{"doi-asserted-by":"publisher","unstructured":"X. Huang, S. Belongie, Arbitrary style transfer in real-time with adaptive instance normalization, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Venice, Italy, 2017), pp. 1501\u20131510. https:\/\/doi.org\/10.1109\/ICCV.2017.167","key":"1035_CR8","DOI":"10.1109\/ICCV.2017.167"},{"key":"1035_CR9","first-page":"386","volume-title":"Universal Style Transfer Via Feature Transforms, in Advances in Neural Information Processing Systems","author":"Y Li","year":"2017","unstructured":"Y. Li, C. Fang, J. Yang, Z. Wang et al., Universal Style Transfer Via Feature Transforms, in Advances in Neural Information Processing Systems (MIT Press, Long Beach, CA, USA, 2017), pp.386\u2013396"},{"doi-asserted-by":"publisher","unstructured":"T. Wang, Y. Zhang, Y. Fan, et al. High-fidelity Gan inversion for image attribute editing, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, New Orleans, LA, USA, 2022), pp. 11379\u201311388. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01109","key":"1035_CR10","DOI":"10.1109\/CVPR52688.2022.01109"},{"doi-asserted-by":"publisher","unstructured":"Y. Yao, J.Q. Ren, X.S. Xie, et al. Attention-aware multi-stroke style transfer, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Long Beach, CA, USA, 2019), pp. 1467\u20131475. https:\/\/doi.org\/10.1109\/CVPR.2019.00156","key":"1035_CR11","DOI":"10.1109\/CVPR.2019.00156"},{"doi-asserted-by":"publisher","unstructured":"S.H. Liu, T.W. Lin, D.L. He, et al. Adaattn: revisit attention mechanism in arbitrary neural style transfer, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Montreal Canada, 2021), pp. 6649\u20136658. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00658","key":"1035_CR12","DOI":"10.1109\/ICCV48922.2021.00658"},{"issue":"08","key":"1035_CR13","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.11999\/JEIT200211","volume":"43","author":"Yu Shen","year":"2021","unstructured":"Yu. Shen, Y. Qian, C. Xiaopeng et al., Structure refinement neural style transfer. J. Electron. Inf. Technol. 43(08), 2361\u20132369 (2021). https:\/\/doi.org\/10.11999\/JEIT200211","journal-title":"J. Electron. Inf. Technol."},{"unstructured":"Y. Deng, F. Tang, X. Pan, et al. StyTr2: Image Style Transfer with Transformers [OL]. https:\/\/arxiv.org\/abs\/2105.14576.","key":"1035_CR14"},{"doi-asserted-by":"publisher","unstructured":"N. Kalischek, J.D. Wegner, K. Schindler, In the light of feature distributions: moment matching for neural style transfer, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Nashville, TN, USA, 2021), pp. 9382\u20139391. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00926","key":"1035_CR15","DOI":"10.1109\/CVPR46437.2021.00926"},{"doi-asserted-by":"publisher","unstructured":"P. Isola, J.Y. Zhu, T. Zhou, et al. Image-to-image translation with conditional adversarial networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Honolulu, HI, USA, 2017), pp. 1125\u20131134. https:\/\/doi.org\/10.1109\/CVPR.2017.632","key":"1035_CR16","DOI":"10.1109\/CVPR.2017.632"},{"doi-asserted-by":"publisher","unstructured":"J. Y. Zhu, T. Park, P. Isola, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Venice, Italy, 2017). https:\/\/doi.org\/10.1109\/ICCV.2017.244","key":"1035_CR17","DOI":"10.1109\/ICCV.2017.244"},{"doi-asserted-by":"crossref","unstructured":"X. Huang, M.Y. Liu, S. Belongie, et al. Multimodal unsupervised image-to-image translation, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 172\u2013189","key":"1035_CR18","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"1035_CR19","first-page":"7198","volume":"33","author":"T Park","year":"2020","unstructured":"T. Park, J.Y. Zhu, O. Wang et al., Swapping autoencoder for deep image manipulation. Adv. Neural. Inf. Process. Syst. 33, 7198\u20137211 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"publisher","unstructured":"Y. Choi, Y. Uh, J. Yoo, et al. StarGAN v2: Diverse image synthesis for multiple domains, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Seattle, WA, USA, 2020), pp. 8188\u20138197. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00821.","key":"1035_CR20","DOI":"10.1109\/CVPR42600.2020.00821"},{"doi-asserted-by":"publisher","unstructured":"T. Karras, S. Laine, T. Aila, A style-based generator architecture for generative adversarial networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Long Beach, CA, USA, 2019), pp. 4401\u20134410. https:\/\/doi.org\/10.1109\/TPAMI.2020.2970919","key":"1035_CR21","DOI":"10.1109\/TPAMI.2020.2970919"},{"doi-asserted-by":"publisher","unstructured":"R. Abdal, Y. Qin, P. Wonka, Image2StyleGAN: how to embed images into the StyleGAN latent space? inProceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, Seoul, Korea (South), 2019), pp. 4432\u20134441. https:\/\/doi.org\/10.1109\/ICCV.2019.00453","key":"1035_CR22","DOI":"10.1109\/ICCV.2019.00453"},{"doi-asserted-by":"crossref","unstructured":"E. Richardson, Y. Alaluf, O. Patashnik, et al. Encoding in style: a stylegan encoder for image-to-image translation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021), pp. 2287\u20132296","key":"1035_CR23","DOI":"10.1109\/CVPR46437.2021.00232"},{"unstructured":"S. Guan, Y. Tai, B. Ni, et al. Collaborative Learning for Faster Stylegan Embedding [EB\/OL]. https:\/\/arxiv.org\/abs\/2007.01758 (2020)","key":"1035_CR24"},{"key":"1035_CR25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185894","author":"D Zhou","year":"2022","unstructured":"D. Zhou, H. Zhang, Q. Li et al., COutfitGAN: learning to synthesize compatible outfits supervised by silhouette masks and fashion styles. IEEE Trans. Multimed. (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3185894","journal-title":"IEEE Trans. Multimed."},{"issue":"6","key":"1035_CR26","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.3390\/s22062199","volume":"22","author":"AE Mahdaoui","year":"2022","unstructured":"A.E. Mahdaoui, A. Ouahabi, M.S. Moulay, Image denoising using a compressive sensing approach based on regularization constraints. Sensors 22(6), 2199 (2022)","journal-title":"Sensors"},{"issue":"7","key":"1035_CR27","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1587\/transinf.2021EDP7033","volume":"104","author":"H Zhou","year":"2021","unstructured":"H. Zhou, H. Xiong, C. Li et al., Single image dehazing based on weighted variational regularized model. IEICE Trans. Inf. Syst. 104(7), 961\u2013969 (2021)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"1035_CR28","doi-asserted-by":"publisher","first-page":"74973","DOI":"10.1109\/ACCESS.2019.2921451","volume":"7","author":"P Liu","year":"2019","unstructured":"P. Liu, H. Zhang, W. Lian et al., Multi-level wavelet convolutional neural networks. IEEE Access 7, 74973\u201374985 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2921451","journal-title":"IEEE Access"},{"key":"1035_CR29","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.neucom.2019.11.044","volume":"382","author":"S Xue","year":"2020","unstructured":"S. Xue, W. Qiu, F. Liu et al., Wavelet-based residual attention network for image super-resolution. Neurocomputing 382, 116\u2013126 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2019.11.044","journal-title":"Neurocomputing"},{"key":"1035_CR30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028688","author":"J Xin","year":"2020","unstructured":"J. Xin, J. Li, X. Jiang et al., Wavelet-based dual recursive network for image super-resolution. IEEE Transactions on Neural Networks and Learning Systems (2020). https:\/\/doi.org\/10.1109\/TNNLS.2020.3028688","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1035_CR31","doi-asserted-by":"publisher","first-page":"3512","DOI":"10.1109\/TGRS.2018.2885506","volume":"57","author":"W Ma","year":"2019","unstructured":"W. Ma, Z. Pan, J. Guo et al., Achieving super-resolution remote sensing images via the wavelet transform combined with the recursive res-net. IEEE Trans. Geosci. Remote Sens. 57, 3512\u20133527 (2019). https:\/\/doi.org\/10.1109\/TGRS.2018.2885506","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"doi-asserted-by":"publisher","unstructured":"T. Guo, H.S. Mousavi, T.H. Vu, et al. Deep wavelet prediction for image super-resolution, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE, Honolulu, HI, USA, 2017), pp. 1100\u20131109. https:\/\/doi.org\/10.1109\/CVPRW.2017.148","key":"1035_CR32","DOI":"10.1109\/CVPRW.2017.148"},{"doi-asserted-by":"crossref","unstructured":"T.Y. Lin, M. Maire, S. Belongie, et al. Microsoft COCO: common objects in context, in Proceedings of the European Conference on Computer Vision (ECCV) (IEEE, Zurich, Switzerland, 2014), pp. 740\u2013755","key":"1035_CR33","DOI":"10.1007\/978-3-319-10602-1_48"},{"unstructured":"K. Nichol, Painter by Numbers, Wikiart. https:\/\/www.kaggle.com\/c\/painter-by-numbers\/. Assessed 20 Nov 2021.","key":"1035_CR34"},{"unstructured":"T. Karras, T. Aila, S. Laine, et al. Progressive growing of GANs for improved quality, stability, and variation [EB\/OL]. arXiv:1710.10196 (2018)","key":"1035_CR35"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01035-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-023-01035-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01035-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T11:03:00Z","timestamp":1687172580000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-023-01035-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1035"],"URL":"https:\/\/doi.org\/10.1186\/s13634-023-01035-w","relation":{},"ISSN":["1687-6180"],"issn-type":[{"type":"electronic","value":"1687-6180"}],"subject":[],"published":{"date-parts":[[2023,6,19]]},"assertion":[{"value":"3 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2023","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":"Competing interests"}}],"article-number":"66"}}