{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T13:32:59Z","timestamp":1767619979840,"version":"3.48.0"},"reference-count":51,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JST SPRING","award":["JP-MJSP2109"],"award-info":[{"award-number":["JP-MJSP2109"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In image sensing, measurements such as an object\u2019s position or contour are typically obtained by analyzing digitized images. This method is widely used due to its simplicity. However, relative motion or inaccurate focus can cause motion and defocus blur, reducing measurement accuracy. Thus, video deblurring is essential. However, existing deep learning-based video deblurring methods struggle to balance high-quality deblurring, fast inference, and wide applicability. First, we propose a Current-Aware Temporal Fusion (CATF) framework, which focuses on the current frame in terms of both network architecture and modules. This reduces interference from unrelated features of neighboring frames and fully exploits current frame information, improving deblurring quality. Second, we introduce a Mixture-of-Experts module based on NAFBlocks (MoNAF), which adaptively selects expert structures according to the input features, reducing inference time. Third, we design a training strategy to support both sequential and temporally parallel inference. In sequential deblurring, we conduct experiments on the DVD, GoPro, and BSD datasets. Qualitative results show that our method effectively preserves image structures and fine details. Quantitative results further demonstrate that our method achieves clear advantages in terms of PSNR and SSIM. In particular, under the exposure setting of 3 ms\u201324 ms on the BSD dataset, our method achieves 33.09 dB PSNR and 0.9453 SSIM, indicating its effectiveness even in severely blurred scenarios. Meanwhile, our method achieves a good balance between deblurring quality and runtime efficiency. Moreover, the framework exhibits minimal error accumulation and performs effectively in temporal parallel computation. These results demonstrate that effective video deblurring serves as an important supporting technology for accurate image sensing.<\/jats:p>","DOI":"10.3390\/s26010321","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:53:50Z","timestamp":1767610430000},"page":"321","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Current-Aware Temporal Fusion with Input-Adaptive Heterogeneous Mixture-of-Experts for Video Deblurring"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1216-9554","authenticated-orcid":false,"given":"Yanwen","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Chiba University, Chiba 263-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Chiba University, Chiba 263-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3181-0818","authenticated-orcid":false,"given":"Akio","family":"Namiki","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Chiba University, Chiba 263-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chang, Y.J., Hsu, M.C., and Liang, W.Y. (2025). Image Sensing for Motorcycle Active Safety Warning System: Using YOLO and Heuristic Weighting Mechanism. Sensors, 25.","DOI":"10.3390\/s25237214"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Katsamenis, I., Bakalos, N., Lappas, A., Protopapadakis, E., Mart\u00edn-Portugu\u00e9s Montoliu, C., Doulamis, A., Doulamis, N., Rallis, I., and Kalogeras, D. (2025). DORIE: Dataset of Road Infrastructure Elements\u2014A Benchmark of YOLO Architectures for Real-Time Patrol Vehicle Monitoring. Sensors, 25.","DOI":"10.3390\/s25216653"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yao, X., Yuan, H., Zhao, S., Tian, W., Han, D., Li, X., Wang, F., and Wang, S. (2025). Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images. Sensors, 25.","DOI":"10.3390\/s25154714"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3801","DOI":"10.1007\/s00371-024-03632-8","article-title":"Deep learning in motion deblurring: Current status, benchmarks and future prospects","volume":"41","author":"Xiang","year":"2025","journal-title":"Vis. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TCSVT.2022.3202361","article-title":"Deep idempotent network for efficient single image blind deblurring","volume":"33","author":"Mao","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chen, L., Chu, X., Zhang, X., and Sun, J. (2022, January 23\u201327). Simple baselines for image restoration. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, D., Zhang, Y., Cheung, K.C., Wang, X., Qin, H., and Li, H. (2022, January 23\u201327). Learning degradation representations for image deblurring. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19797-0_42"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gong, D., Yang, J., Liu, L., Zhang, Y., Reid, I., Shen, C., van den Hengel, A., and Shi, Q. (2017, January 21\u201326). From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.405"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2021, January 20\u201325). Multi-stage progressive image restoration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cho, S.J., Ji, S.W., Hong, J.P., Jung, S.W., and Ko, S.J. (2021, January 10\u201317). Rethinking coarse-to-fine approach in single image deblurring. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.neucom.2022.10.028","article-title":"Lightweight MIMO-WNet for single image deblurring","volume":"516","author":"Liu","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s00371-023-02771-8","article-title":"Reference-based dual-task framework for motion deblurring","volume":"40","author":"Liu","year":"2024","journal-title":"Vis. Comput."},{"key":"ref_13","unstructured":"Zou, H., Suganuma, M., and Okatani, T. (2023). Reference-based motion blur removal: Learning to utilize sharpness in the reference image. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2245","DOI":"10.1109\/TIP.2022.3142518","article-title":"Deep ranking exemplar-based dynamic scene deblurring","volume":"31","author":"Li","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., and Guo, B. (2020, January 13\u201319). Learning texture transformer network for image super-resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref_16","unstructured":"Zhu, C., Dong, H., Pan, J., Liang, B., Huang, Y., Fu, L., and Wang, F. (March, January 22). Deep recurrent neural network with multi-scale bi-directional propagation for video deblurring. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Gao, Y., Zheng, Y., and Zheng, B. (2020, January 23\u201328). Efficient spatio-temporal recurrent neural network for video deblurring. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58539-6_12"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ji, B., and Yao, A. (2022, January 18\u201324). Multi-scale memory-based video deblurring. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00196"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, C., Wang, X., Fan, Y., Li, S., and Qian, X. (2024, January 20\u201327). Decoupling degradations with recurrent network for video restoration in under-display camera. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i4.28144"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xie, H., and Yao, H. (2022, January 23\u201327). Spatio-temporal deformable attention network for video deblurring. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19787-1_33"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/TCSVT.2022.3201045","article-title":"VDTR: Video Deblurring with Transformer","volume":"33","author":"Cao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, X., Chan, K.C., Yu, K., Dong, C., and Change Loy, C. (2019, January 16-17). Edvr: Video restoration with enhanced deformable convolutional networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2171","DOI":"10.1109\/TIP.2024.3372454","article-title":"Vrt: A video restoration transformer","volume":"33","author":"Liang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6354","DOI":"10.1109\/TIP.2024.3482176","article-title":"Deblurring Videos Using Spatial-Temporal Contextual Transformer with Feature Propagation","volume":"33","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","unstructured":"So, J., Lee, J., and Park, E. (October, January 29). Frdiff: Feature reuse for universal training-free acceleration of diffusion models. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Boucherit, I., and Kheddar, H. (2025). Reinforced Residual Encoder\u2013Decoder Network for Image Denoising via Deeper Encoding and Balanced Skip Connections. Big Data Cogn. Comput., 9.","DOI":"10.3390\/bdcc9040082"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chu, X., Chen, L., Chen, C., and Lu, X. (2022, January 23\u201327). Improving image restoration by revisiting global information aggregation. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20071-7_4"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"7762","DOI":"10.1109\/TCSVT.2025.3544314","article-title":"Long short-term fusion by multi-scale distillation for screen content video quality enhancement","volume":"35","author":"Huang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"8976","DOI":"10.1109\/TIP.2020.3023534","article-title":"Deep video deblurring using sharpness features from exemplars","volume":"29","author":"Xiang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3957","DOI":"10.1109\/TCSVT.2023.3325408","article-title":"Learning spatio-temporal sharpness map for video deblurring","volume":"34","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"7430","DOI":"10.1109\/TCSVT.2024.3369073","article-title":"LightViD: Efficient Video Deblurring with Spatial\u2013Temporal Feature Fusion","volume":"34","author":"Lin","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_33","unstructured":"Cao, J., Li, Y., Zhang, K., and Van Gool, L. (2021). Video super-resolution transformer. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1986","DOI":"10.1109\/TCSVT.2021.3093928","article-title":"Multi-attention convolutional neural network for video deblurring","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Li, D., Xu, C., Zhang, K., Yu, X., Zhong, Y., Ren, W., Suominen, H., and Li, H. (2021, January 20\u201325). Arvo: Learning all-range volumetric correspondence for video deblurring. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00763"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., and Wang, O. (2017, January 21\u201326). Deep Video Deblurring for Hand-Held Cameras. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.33"},{"key":"ref_37","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_38","unstructured":"Zhou, S., Zhang, J., Pan, J., Xie, H., Zuo, W., and Ren, J. (November, January 27). Spatio-temporal filter adaptive network for video deblurring. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453720","article-title":"Recurrent video deblurring with blur-invariant motion estimation and pixel volumes","volume":"40","author":"Son","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"12581","DOI":"10.1109\/TCSVT.2024.3432612","article-title":"Efficiently exploiting spatially variant knowledge for video deblurring","volume":"34","author":"Xu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_41","unstructured":"Park, N., and Kim, S. (2022). How do vision transformers work?. arXiv."},{"key":"ref_42","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., and Dean, J. (2017). Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv."},{"key":"ref_43","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Nah, S., Hyun Kim, T., and Mu Lee, K. (2017, January 21\u201326). Deep multi-scale convolutional neural network for dynamic scene deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Pan, J., Bai, H., and Tang, J. (2020, January 13\u201319). Cascaded deep video deblurring using temporal sharpness prior. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00311"},{"key":"ref_46","unstructured":"Lin, J., Cai, Y., Hu, X., Wang, H., Yan, Y., Zou, X., Ding, H., Zhang, Y., Timofte, R., and Van Gool, L. (2022). Flow-guided sparse transformer for video deblurring. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5575","DOI":"10.1109\/TCSVT.2025.3531003","article-title":"Attentive Large Kernel Network With Mixture of Experts for Video Deblurring","volume":"35","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Korhonen, J., and You, J. (2012, January 5\u20137). Peak signal-to-noise ratio revisited: Is simple beautiful?. Proceedings of the 2012 Fourth International Workshop on Quality of Multimedia Experience, Melbourne, VIC, Australia.","DOI":"10.1109\/QoMEX.2012.6263880"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201322). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_51","unstructured":"Wang, J., Chan, K.C., and Loy, C.C. (2023, January 7\u201314). Exploring clip for assessing the look and feel of images. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/321\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:57:05Z","timestamp":1767610625000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,4]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010321"],"URL":"https:\/\/doi.org\/10.3390\/s26010321","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,4]]}}}