{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T14:14:08Z","timestamp":1770905648923,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Adverse weather removal aims to restore images degraded by haze, rain, or snow. However, existing unified models often rely on implicit degradation cues, making them vulnerable to inaccurate weather perception and insufficient semantic guidance, which leads to over-smoothing or residual artifacts in real scenes. In this work, we propose AWR-VIP, a prior-guided adverse weather removal framework that explicitly extracts semantic and perceptual priors using a frozen vision\u2013language model (VLM). Given a degraded input, we first employ a degradation-aware prompt extractor to produce a compact set of semantic tags describing key objects and regions, and simultaneously perform weather-type perception by prompting the VLM with explicit weather definitions. Conditioned on the predicted weather type and selected tags, the VLM further generates two levels of restoration guidance: a global instruction that summarizes image-level enhancement goals (e.g., visibility\/contrast) and local instructions that specify tag-aware refinement cues (e.g., recover textures for specific regions). These textual outputs are encoded by a text encoder into a pair of priors (Pglobal and Plocal), which are injected into a UNet-based restorer through global-prior-modulated normalization and instruction-guided attention, enabling weather-adaptive and content-aware restoration. Extensive experiments on a combined benchmark show that AWR-VIP consistently outperforms state-of-the-art methods. Moreover, the VLM-derived priors are plug-and-play and can be integrated into other restoration backbones to further improve performance.<\/jats:p>","DOI":"10.3390\/make8020045","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T12:05:46Z","timestamp":1770897946000},"page":"45","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Adaptive Adverse Weather Removal via Semantic and Low-Level Visual Perceptual Priors"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6109-5099","authenticated-orcid":false,"given":"Wei","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, McMaster Univeristy, Hamilton, ON L8S 4L8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7650-0755","authenticated-orcid":false,"given":"Han","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McMaster Univeristy, Hamilton, ON L8S 4L8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9062-1539","authenticated-orcid":false,"given":"Terry","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McMaster Univeristy, Hamilton, ON L8S 4L8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8084-9332","authenticated-orcid":false,"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McMaster Univeristy, Hamilton, ON L8S 4L8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/MVT.2019.2892497","article-title":"The impact of adverse weather conditions on autonomous vehicles: How rain, snow, fog, and hail affect the performance of a self-driving car","volume":"14","author":"Zang","year":"2019","journal-title":"IEEE Veh. Technol. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Li, R., Cheong, L.-F., and Tan, R.T. (2019). Heavy rain image restoration: Integrating physics model and conditional adversarial learning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00173"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"7043","DOI":"10.1109\/TMM.2024.3359480","article-title":"A Prior Guided Wavelet-Spatial Dual Attention Transformer Framework for Heavy Rain Image Restoration","volume":"26","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chen, W.T., Fang, H.Y., Hsieh, C.L., Tsai, C.C., Chen, I., Ding, J.J., and Kuo, S.Y. (2021). All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00416"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7419","DOI":"10.1109\/TIP.2021.3104166","article-title":"Deep dense multi-scale network for snow removal using semantic and depth priors","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017). AOD-Net: All-in-one dehazing network. 2017 IEEE International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2017.511"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5187","DOI":"10.1109\/TIP.2016.2598681","article-title":"DehazeNet: An end-to-end system for single image haze removal","volume":"25","author":"Cai","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8457","DOI":"10.1109\/TIP.2020.3016134","article-title":"Zero-shot image dehazing","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.1109\/TIP.2023.3256763","article-title":"Vision transformers for single image dehazing","volume":"32","author":"Song","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_10","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"Volume 25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25 (NIPS 2012)"},{"key":"ref_11","first-page":"5998","article-title":"Attention is all you need","volume":"Volume 30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)"},{"key":"ref_12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"Volume 33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 (NeurIPS 2020)"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2944","DOI":"10.1109\/TIP.2017.2691802","article-title":"Clearing the skies: A deep network architecture for single-image rain removal","volume":"26","author":"Fu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhou, H., Dong, W., and Chen, J. (2025). LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors. 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.02010"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, R., Tan, R.T., and Cheong, L.-F. (2020). All in one bad weather removal using architectural search. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.00324"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, T., Fu, X., Yang, X., Guo, X., Dai, J., Qiao, Y., and Hu, X. (2023). Learning weather-general and weather-specific features for image restoration under multiple adverse weather conditions. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.02083"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Yasarla, R., and Patel, V.M. (2022). TransWeather: Transformer-based restoration of images degraded by adverse weather conditions. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00239"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ye, T., Chen, S., Bai, J., Shi, J., Xue, C., Jiang, J., Yin, J., Chen, E., and Liu, Y. (2023). Adverse weather removal with codebook priors. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01163"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yang, H., Pan, L., Yang, Y., and Liang, W. (2024). Language-driven All-in-one Adverse Weather Removal. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.02352"},{"key":"ref_20","first-page":"71275","article-title":"PromptIR: Prompting for All-in-One Blind Image Restoration","volume":"Volume 36","author":"Potlapalli","year":"2023","journal-title":"Advances in Neural Information Processing Systems 36 NeurIPS 2023"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gao, N., Zhong, Y., Chao, F., and Ji, R. (2024). Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration. arXiv.","DOI":"10.2139\/ssrn.5538174"},{"key":"ref_22","unstructured":"Hu, J., Jin, L., Yao, Z., and Lu, Y. (2025). Universal Image Restoration Pre-training via Degradation Classification. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, Z., Xue, T., and Gu, J. (2024). AutoDir: Automatic all-in-one image restoration with latent diffusion. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-73661-2_19"},{"key":"ref_24","unstructured":"Luo, Z., Gustafsson, F.K., Zhao, Z., Sj\u00f6lund, J., and Sch\u00f6n, T.B. (2023). Controlling vision-language models for universal image restoration. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zeng, H., Wang, X., Chen, Y., Su, J., and Liu, J. (2025). Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks. 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.00705"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Dong, W., Zhou, H., Wang, R., Liu, X., Zhai, G., and Chen, J. (2024). DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW63382.2024.00642"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhou, H., Dong, W., Liu, Y., and Chen, J. (2023). Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method Based on Fast Fourier Convolution and ConvNeXt. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW59228.2023.00187"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ancuti, C.O., Ancuti, C., Vasluianu, F.-A., Timofte, R., Zhou, H., Dong, W., Liu, Y., Chen, J., Liu, H., and Li, L. (2023). NTIRE 2023 HR Nonhomogeneous Dehazing Challenge Report. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW59228.2023.00180"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ancuti, C.O., Ancuti, C., Vasluianu, F.-A., Timofte, R., Liu, Y., Wang, X., Zhu, Y., Shi, G., Lu, X., and Fu, X. (2024). NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW63382.2024.00646"},{"key":"ref_30","unstructured":"Li, Z., Lei, Y., Ma, C., Zhang, J., and Shan, H. (2023). Prompt-In-Prompt Learning for Universal Image Restoration. arXiv."},{"key":"ref_31","unstructured":"Kong, X., Dong, C., and Zhang, L. (2024). Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"7650","DOI":"10.1109\/ACCESS.2025.3526168","article-title":"Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal","volume":"13","author":"Chen","year":"2025","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Guo, Y., Gao, Y., Lu, Y., Zhu, H., Liu, R.W., and He, S. (2024). OneRestore: A Universal Restoration Framework for Composite Degradation. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72655-2_15"},{"key":"ref_34","unstructured":"Rajagopalan, S., and Patel, V.M. (March, January 25). AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_35","unstructured":"Bai, Y., Wang, C., Xie, S., Dong, C., Yuan, C., and Wang, Z. (2023). TextIR: A Simple Framework for Text-Based Editable Image Restoration. arXiv."},{"key":"ref_36","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume":"Volume 139","author":"Radford","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., and Efros, A.A. (2023). InstructPix2Pix: Learning to Follow Image Editing Instructions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), PMLR.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Conde, M.V., Geigle, G., and Timofte, R. (2024). InstructIR: High-Quality Image Restoration Following Human Instructions. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72764-1_1"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhu, H., Zhang, Z., Zhang, E., Chen, C., Liao, L., Li, C., Wang, A., Sun, W., and Yan, Q. (2024). Towards Open-Ended Visual Quality Comparison. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72646-0_21"},{"key":"ref_40","unstructured":"Liu, S., Ma, J., Sun, L., Kong, X., and Zhang, L. (2025). InstructRestore: Region-Customized Image Restoration with Human Instructions. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhang, Z., Zhang, E., Chen, C., Liao, L., Wang, A., Xu, K., Li, C., Hou, J., and Zhai, G. (2024). Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref_42","unstructured":"Zhou, H., Dong, W., Liu, X., Zhang, Y., Zhai, G., and Chen, J. (March, January 25). Low-light Image Enhancement via Generative Perceptual Priors. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, PA, USA."},{"key":"ref_43","unstructured":"Dong, W., Zhou, H., Lin, J., and Chen, J. (2025). Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation. arXiv."},{"key":"ref_44","first-page":"34892","article-title":"Visual Instruction Tuning","volume":"Volume 36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wu, R., Yang, T., Sun, L., Zhang, Z., Li, S., and Zhang, L. (2024). SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Chen, L., Chu, X., Zhang, X., and Sun, J. (2022). Simple Baselines for Image Restoration. Computer Vision\u2013ECCV 2022, Springer.","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1109\/TIP.2018.2867951","article-title":"Benchmarking Single-Image Dehazing and Beyond","volume":"28","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Yang, W., Tan, R.T., Feng, J., Liu, J., Guo, Z., and Yan, S. (2017). Deep Joint Rain Detection and Removal From a Single Image. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"3064","DOI":"10.1109\/TIP.2018.2806202","article-title":"DesnowNet: Context-Aware Deep Network for Snow Removal","volume":"27","author":"Liu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"6947","DOI":"10.1109\/TIP.2020.2995264","article-title":"Dehazing Evaluation: Real-World Benchmark Datasets, Criteria, and Baselines","volume":"29","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.-H. (2022). Restormer: Efficient Transformer for High-Resolution Image Restoration. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Gao, X., Wang, R., and Cao, X. (2024). Restoring Images in Adverse Weather Conditions via Histogram Transformer. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72670-5_7"},{"key":"ref_53","unstructured":"Wu, J., Yang, Z., Wang, Z., and Jin, Z. (2025). Beyond Degradation Conditions: All-in-One Image Restoration via HOG Transformers. arXiv."},{"key":"ref_54","unstructured":"Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep Retinex Decomposition for Low-Light Enhancement. arXiv."},{"key":"ref_55","unstructured":"Dong, W., Zhou, H., Zhang, Y., Liu, X., and Chen, J. (2024). ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction. Advances in Neural Information Processing Systems (NeurIPS), Curran Associates, Inc."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Zhou, H., Dong, W., Liu, X., Liu, S., Min, X., Zhai, G., and Chen, J. (2024). Glare: Low Light Image Enhancement via Generative Latent Feature Based Codebook Retrieval. Computer Vision\u2013ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-73195-2_3"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Ancuti, C.O., Ancuti, C., and Timofte, R. (2020). NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW50498.2020.00230"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"5372","DOI":"10.1109\/TIP.2013.2284059","article-title":"Contrast Enhancement Based on Layered Difference Representation of 2D Histograms","volume":"22","author":"Lee","year":"2013","journal-title":"IEEE Trans. Image Process."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/2\/45\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T13:23:35Z","timestamp":1770902615000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/2\/45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,12]]},"references-count":58,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["make8020045"],"URL":"https:\/\/doi.org\/10.3390\/make8020045","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,12]]}}}