請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87137
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕 | zh_TW |
dc.contributor.advisor | Yung-Yu Chuang | en |
dc.contributor.author | 陳柏妤 | zh_TW |
dc.contributor.author | Bo-Yu Chen | en |
dc.date.accessioned | 2023-05-10T16:10:36Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-05-10 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-02-14 | - |
dc.identifier.citation | [1] T.Brooks,B.Mildenhall,T.Xue,J.Chen,D.Sharlet,andJ.T.Barron.Unprocessing images for learned raw denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11036–11045, 2019.
[2] Y. Cai, X. Hu, H. Wang, Y. Zhang, H. Pfister, and D. Wei. Learning to generate realistic noisy images via pixel-level noise-aware adversarial training. Advances in Neural Information Processing Systems, 34:3259–3270, 2021. [3] M. Chang, Q. Li, H. Feng, and Z. Xu. Spatial-adaptive network for single image denoising. In European Conference on Computer Vision, pages 171–187. Springer, 2020. [4] J. Chen, J. Chen, H. Chao, and M. Yang. Image blind denoising with generative adversarial network based noise modeling. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3155–3164, 2018. [5] L. Chen, X. Chu, X. Zhang, and J. Sun. Simple baselines for image restoration. arXiv preprint arXiv:2204.04676, 2022. [6] S.Guo,Z.Yan,K.Zhang,W.Zuo,andL.Zhang. Toward convolutional blind denoising of real photographs. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1712–1722, 2019. [7] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [8] T. Huang, S. Li, X. Jia, H. Lu, and J. Liu. Neighbor2neighbor: Self-supervised denoising from single noisy images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14781–14790, 2021. [9] D.-W. Kim, J. Ryun Chung, and S.-W. Jung. Grdn: Grouped residual dense network for real image denoising and gan-based real-world noise modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 0–0, 2019. [10] J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, and T. Aila. Noise2noise: Learning image restoration without clean data. arXiv preprint arXiv:1803.04189, 2018. [11] J.Li,J.Zhang,S.J.Maybank,and D.Tao.Bridging composite and real:towards end-to-end deep image matting. International Journal of Computer Vision, 130(2):246– 266, 2022. [12] Y. Liu, Z. Qin, S. Anwar, P. Ji, D. Kim, S. Caldwell, and T. Gedeon. Invertible denoising network: A light solution for real noise removal. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13365– 13374, 2021. [13] O.Ronneberger,P.Fischer,andT.Brox.U-net:Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015. [14] K. Wei, Y. Fu, J. Yang, and H. Huang. A physics-based noise formation model for extreme low-light raw denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2758–2767, 2020. [15] X. Wu, M. Liu, Y. Cao, D. Ren, and W. Zuo. Unpaired learning of deep image denoising. In European conference on computer vision, pages 352–368. Springer, 2020. [16] Z. Yue, Q. Zhao, L. Zhang, and D. Meng. Dual adversarial network: Toward real-world noise removal and noise generation. In European Conference on Computer Vision, pages 41–58. Springer, 2020. [17] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao. Cycleisp: Real image restoration via improved data synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2696– 2705, 2020. [18] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14821–14831, 2021. [19] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao. Learning enriched features for fast image restoration and enhancement. arXiv preprint arXiv:2205.01649, 2022. [20] K. Zhang, Y. Li, W. Zuo, L. Zhang, L. Van Gool, and R. Timofte. Plug-and-play image restoration with deep denoiser prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021. [21] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing, 26(7):3142–3155, 2017. [22] K.Zhang, W.Zuo, and L.Zhang. Ffdnet: Toward a fast and flexible solution for cnn-based image denoising. IEEE Transactions on Image Processing, 27(9):4608–4622, 2018. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87137 | - |
dc.description.abstract | 「影像去噪」旨在消除由電子傳輸、圖像信號處理和圖片壓縮產生的噪聲,是電腦視覺領域的一個重要研究主題。它可以幫助提高影像品質,且能增進後續其他任務的表現,像是:影像分類、物件偵測、物件分割等。「基於影像語意的影像增強」指的是將照片根據語意劃分為多個區域(例如:天空、樹、人),並根據每種區域不同的特性施以專門的降噪器或美化器。
在這篇論文中,我們專注於使用深度學習網路做天空區域的去噪,並以此為目標進行以下三步驟。首先,調查使用深度學習進行影像去噪最核心的兩個議題:網路架構設計與生成噪聲影像。我們調查了近幾年的研究是如何解決這兩個問題,並對其做分類與歸納。再者,為了選出最有潛力的降噪器,我們把來自十篇不同研究的降噪器測試在天空的噪聲圖片上,並採用表現最好的網路進行後續的重新訓練。最後,為了提高降噪器的表現,我們嘗試了不同的噪聲合成步驟,並選用效果最好的來訓練最終的模型。 | zh_TW |
dc.description.abstract | Image denoising aims to remove the noise from degraded observations generated from the electronic transmission, image signal process pipeline, and compression. Image denoising is a prevalent research topic in computer vision, and assists in enhancing image quality and improving the performance of high-level computer vision tasks, such as image classification, object detection, and object segmentation.Segment-based enhancement divides a photo into semantic-based regions, and enhances each region with different beautifiers and denoisers according to the semantic domain knowledge.
In this paper, we focus on sky denoising with deep learning approaches. To achieve this goal, we execute the following three steps: First, we survey and summarize how the widely-used and state-of-the-art researches tackle the two critical components of image denoising: model architecture and noise data synthesis. Secondly, we execute a pilot study on ten different denoisers, which have released the pre-trained models, and we retrain the best-performing model on our sky dataset. Finally, we try different procedures of noise synthesis to improve the retaining performance and select the best one to train our final model. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-05-10T16:10:36Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-05-10T16:10:36Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xi List of Tables xiii Chapter 1 Introduction 1 Chapter 2 Deep Learning Methods for Image Denoising 5 2.1 Model Architecture 5 2.1.1 Denoise Model Architecture 5 2.1.1.1 The single-scale feature pipeline 6 2.1.1.2 The encoder-decoder models 8 2.1.1.3 The multi-scale feature pipeline 8 2.1.2 Noise Level Information and Non-Blind Denoiser 9 2.2 Learning Strategies 11 2.2.1 Training with Pair Data 11 2.2.2 Training with Unpair Data 11 2.2.2.1 Use Unpair Clean-Noise Data 11 2.2.2.2 Use Multiple Noise Data 12 2.2.2.3 Use Single Noise Data 12 Chapter 3 Noisy Data Synthesis 15 3.1 Synthesize Noise Data by Additive White Noise 15 3.2 Synthesize Noise Data by Physics-Based Model 16 3.3 Synthesize Noise Data by Modeling the Image Signal Processing Pipeline 17 3.4 Synthesize Noise Data by Generative Adversarial Network 18 Chapter 4 Experiment 21 4.1 Dataset 21 4.2 Pilot Study 22 4.3 Retrain Setting 24 4.4 Data Synthesis 24 4.4.1 From pre-trained GAN model 25 4.4.2 Add different Gaussian noise on each channel 25 4.4.3 Add identical Gaussian noise on each channel 25 4.5 Other Trick 28 4.5.1 Deal with Patch Artifact 28 4.5.2 The Combination with Noisy Foreground 33 4.6 Visual Result 34 Chapter 5 Conclusion 39 References 41 | - |
dc.language.iso | en | - |
dc.title | 使用深度學習模型進行天空去噪 | zh_TW |
dc.title | Implementation of Sky Denoising through Deep Learning Approaches | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-1 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 吳賦哲;葉正聖 | zh_TW |
dc.contributor.oralexamcommittee | Fu-Che Wu;Jeng-Sheng Yeh | en |
dc.subject.keyword | 去噪,天空去噪,深度學習,噪聲合成, | zh_TW |
dc.subject.keyword | Denoising,Sky Denoising,Deep Learning,Noise Synthesis, | en |
dc.relation.page | 44 | - |
dc.identifier.doi | 10.6342/NTU202300316 | - |
dc.rights.note | 未授權 | - |
dc.date.accepted | 2023-02-15 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資訊工程學系 | - |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-1.pdf 目前未授權公開取用 | 108.39 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。