1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Theses
  5. Item

學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 基於知識萃取之內容解構影像去反射
Image Reflection Removal based on Knowledge-distilling Content Disentanglement
作者 鄭楷翰
Cheng, Kai-Han
貢獻者 彭彥璁
Peng, Yan-Tsung
鄭楷翰
Cheng, Kai-Han
關鍵詞 影像處理
影像去反射
Image Processing
Image reflection removal
日期 2021
上傳時間 1-Nov-2021 11:59:48 (UTC+8)
摘要 當我們通過玻璃等透明介質拍攝照片時，可能會出現不可避免的反射，模糊了我們想要捕捉的場景。我們提出了一種基於知識蒸餾的方式來將影像內容進行透射層及反射層的分解，進一步解決影像反射的問題。透過實驗證明，該模型具有一定的清除反射之能力。
When we shoot pictures through transparent media, such as glass, reflection can undesirably occur, obscuring the scene we intended to capture. Therefore, removing reflection is practical in image restoration. However, a reflective scene mixed with that behind the glass is challenging to be separated, considered significantly ill-posed. This letter addresses the single image reflection removal (SIRR) problem by proposing a knowledge-distilling-based content disentangling model that can effectively decompose the transmission and reflection layers. The experiments on benchmark SIRR datasets demonstrate that our method performs favorably against state-of-the-art SIRR methods.
參考文獻 [1] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C Kot, "Benchmarking single-image reflection removal algorithms," in Int. Conf. Comput. Vis., 2017.
[2] Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, and Hua Huang, "Single image reflection removal exploiting misaligned training data and network enhancements," in IEEE Conf. Comput. Vis. Pattern Recog. , 2019.
[3] Patrick Wieschollek, Orazio Gallo, Jinwei Gu, and Jan Kautz, “Separating reflection and transmission images in the wild,” in Eur. Conf. Comput. Vis., 2018, pp. 89–104.
[4] Jie Yang, Dong Gong, Lingqiao Liu, and Qinfeng Shi, "Seeing deeply and bidirectionally: A deep learning approach for single image reflection removal," in Eur. Conf. Comput. Vis., 2018.
[5] Xuaner Zhang, Ren Ng, and Qifeng Chen, "Single image reflection separation with perceptual losses," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.
[6] Soomin Kim, Yuchi Huo, and Sung-Eui Yoon, "Single image reflection removal with physically-based training images," in IEEE Conf. Comput. Vis. Pattern Recog., 2020.
[7] Jun Sun, Yakun Chang, Cheolkon Jung, and Jiawei Feng, "Multi-modal reflection removal using convolutional neural networks," IEEE Sign. Process. Letters, 2019.
[8] Tingtian Li and Daniel P. K. Lun, "Single-image reflection removal via a two-stage background recovery process," IEEE Sign. Process. Letters , 2019.
[9] Nikolaos Arvanitopoulos, Radhakrishna Achanta, and Sabine Susstrunk, "Single image reflection suppression," in IEEE Conf. Comput. Vis. Pattern Recog., 2017.
[10] Yu Li and Michael S Brown, "Single image layer separation using relative smoothness," in IEEE Conf. Comput. Vis. Pattern Recog., 2014.
[11] Renjie Wan, Boxin Shi, Tan Ah Hwee, and Alex C Kot, "Depth of field guided reflection removal," in IEEE Int. Conf. Image Process. IEEE, 2016.
[12] Xiaojie Guo, Xiaochun Cao, and Yi Ma, "Robust separation of reflection from multiple images," in IEEE Conf. Comput. Vis. Pattern Recog. , 2014.
[13] Richard Szeliski, Shai Avidan, and Padmanabhan Anandan, "Layer extraction from multiple images containing reflections and transparency," in IEEE Conf. Comput. Vis. Pattern Recog., 2000. [14] Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, and David Wipf, "A generic deep architecture for single image reflection removal and image smoothing," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3238–3247.
[15] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C. Kot, "Crrn: Multi-scale guided concurrent reflection removal network," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.
[16] Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh, "Generative single image reflection separation," arXiv preprint arXiv:1801.04102 , 2018.
[17] Ya-Chu Chang, Chia-Ni Lu, Chia-Chi Cheng, and Wei-Chen Chiu, "Single image reflection removal with edge guidance, reflection classifier, and recurrent decomposition," in IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.
[18] Chao Li, Yixiao Yang, Kun He, Stephen Lin, and John E Hopcroft, "Single image reflection removal through cascaded refinement," in IEEE Conf. Comput. Vis. Pattern Recog., 2020.
[19] Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chung-Chi Tsai, and Chia Wen Lin, "Banet: Blur-aware attention networks for dynamic scene deblurring," arXiv preprint arXiv:2101.07518, 2021.
[20] Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean, "Distilling the knowledge in a neural network," in NIPS Deep Learning and Representation Learning Workshop, 2015.
[21] Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Y. Bengio, "Fitnets: Hints for thin deep nets," in Int. Conf. Learn. Represent., 2015.
[22] Yifan Liu, Ke Chen, Chris Liu, Zengchang Qin, Zhenbo Luo, and Jingdong Wang, "Structured knowledge distillation for semantic segmentation," in IEEE Conf. Comput. Vis. Pattern Recog., 2019. [23] Tao Wang, Li Yuan, Xiaopeng Zhang, and Jiashi Feng, "Distilling object detectors with fine-grained feature imitation," in IEEE Conf. Comput. Vis. Pattern Recog., 2019.
[24] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. International Journal of Computer Vision, 111(1), 98-136, 2015
[25] Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang, "The unreasonable effectiveness of deep features as a perceptual metric," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.
描述 碩士
國立政治大學
資訊科學系
108753143
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108753143
資料類型 thesis
dc.contributor.advisor 彭彥璁zh_TW
dc.contributor.advisor Peng, Yan-Tsungen_US
dc.contributor.author (Authors) 鄭楷翰zh_TW
dc.contributor.author (Authors) Cheng, Kai-Hanen_US
dc.creator (作者) 鄭楷翰zh_TW
dc.creator (作者) Cheng, Kai-Hanen_US
dc.date (日期) 2021en_US
dc.date.accessioned 1-Nov-2021 11:59:48 (UTC+8)-
dc.date.available 1-Nov-2021 11:59:48 (UTC+8)-
dc.date.issued (上傳時間) 1-Nov-2021 11:59:48 (UTC+8)-
dc.identifier (Other Identifiers) G0108753143en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/137674-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學系zh_TW
dc.description (描述) 108753143zh_TW
dc.description.abstract (摘要) 當我們通過玻璃等透明介質拍攝照片時，可能會出現不可避免的反射，模糊了我們想要捕捉的場景。我們提出了一種基於知識蒸餾的方式來將影像內容進行透射層及反射層的分解，進一步解決影像反射的問題。透過實驗證明，該模型具有一定的清除反射之能力。zh_TW
dc.description.abstract (摘要) When we shoot pictures through transparent media, such as glass, reflection can undesirably occur, obscuring the scene we intended to capture. Therefore, removing reflection is practical in image restoration. However, a reflective scene mixed with that behind the glass is challenging to be separated, considered significantly ill-posed. This letter addresses the single image reflection removal (SIRR) problem by proposing a knowledge-distilling-based content disentangling model that can effectively decompose the transmission and reflection layers. The experiments on benchmark SIRR datasets demonstrate that our method performs favorably against state-of-the-art SIRR methods.en_US
dc.description.tableofcontents 摘要 I
ABSTRACT II
TABLE OF CONTENTS III
LIST OF FIGURES V
LIST OF TABLES IV
1. INTRODUCTION 1
1.1. Motivation and Challenges 1
1.2. Contributions 2
1.3. Thesis Structure 3
2. RELATED WORKS 4
2.1. Single Image Reflection Removal 4
2.2. Knowledge Distillation 6
3. METHODOLOGY 8
3.1 Network Architecture 8
3.2 Loss functions 10
4. Dataset 13
4.1. Synthetic data 13
4.2. Real world data 15
4.3. Our data collection 18
5. EXPERIMENTAL RESULTS 21
5.1. Dataset and environment detail 21
5.2. Evaluation metrics 21
5.3. Quantitative comparison 22
5.4. Ablation study 24
5.5. Qualitative results 24
6. CONCLUSIONS 28
REFERENCES 29		zh_TW
dc.format.extent 1812293 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108753143en_US
dc.subject (關鍵詞) 影像處理zh_TW
dc.subject (關鍵詞) 影像去反射zh_TW
dc.subject (關鍵詞) Image Processingen_US
dc.subject (關鍵詞) Image reflection removalen_US
dc.title (題名) 基於知識萃取之內容解構影像去反射zh_TW
dc.title (題名) Image Reflection Removal based on Knowledge-distilling Content Disentanglementen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C Kot, "Benchmarking single-image reflection removal algorithms," in Int. Conf. Comput. Vis., 2017.
[2] Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, and Hua Huang, "Single image reflection removal exploiting misaligned training data and network enhancements," in IEEE Conf. Comput. Vis. Pattern Recog. , 2019.
[3] Patrick Wieschollek, Orazio Gallo, Jinwei Gu, and Jan Kautz, “Separating reflection and transmission images in the wild,” in Eur. Conf. Comput. Vis., 2018, pp. 89–104.
[4] Jie Yang, Dong Gong, Lingqiao Liu, and Qinfeng Shi, "Seeing deeply and bidirectionally: A deep learning approach for single image reflection removal," in Eur. Conf. Comput. Vis., 2018.
[5] Xuaner Zhang, Ren Ng, and Qifeng Chen, "Single image reflection separation with perceptual losses," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.
[6] Soomin Kim, Yuchi Huo, and Sung-Eui Yoon, "Single image reflection removal with physically-based training images," in IEEE Conf. Comput. Vis. Pattern Recog., 2020.
[7] Jun Sun, Yakun Chang, Cheolkon Jung, and Jiawei Feng, "Multi-modal reflection removal using convolutional neural networks," IEEE Sign. Process. Letters, 2019.
[8] Tingtian Li and Daniel P. K. Lun, "Single-image reflection removal via a two-stage background recovery process," IEEE Sign. Process. Letters , 2019.
[9] Nikolaos Arvanitopoulos, Radhakrishna Achanta, and Sabine Susstrunk, "Single image reflection suppression," in IEEE Conf. Comput. Vis. Pattern Recog., 2017.
[10] Yu Li and Michael S Brown, "Single image layer separation using relative smoothness," in IEEE Conf. Comput. Vis. Pattern Recog., 2014.
[11] Renjie Wan, Boxin Shi, Tan Ah Hwee, and Alex C Kot, "Depth of field guided reflection removal," in IEEE Int. Conf. Image Process. IEEE, 2016.
[12] Xiaojie Guo, Xiaochun Cao, and Yi Ma, "Robust separation of reflection from multiple images," in IEEE Conf. Comput. Vis. Pattern Recog. , 2014.
[13] Richard Szeliski, Shai Avidan, and Padmanabhan Anandan, "Layer extraction from multiple images containing reflections and transparency," in IEEE Conf. Comput. Vis. Pattern Recog., 2000. [14] Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, and David Wipf, "A generic deep architecture for single image reflection removal and image smoothing," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3238–3247.
[15] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C. Kot, "Crrn: Multi-scale guided concurrent reflection removal network," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.
[16] Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh, "Generative single image reflection separation," arXiv preprint arXiv:1801.04102 , 2018.
[17] Ya-Chu Chang, Chia-Ni Lu, Chia-Chi Cheng, and Wei-Chen Chiu, "Single image reflection removal with edge guidance, reflection classifier, and recurrent decomposition," in IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.
[18] Chao Li, Yixiao Yang, Kun He, Stephen Lin, and John E Hopcroft, "Single image reflection removal through cascaded refinement," in IEEE Conf. Comput. Vis. Pattern Recog., 2020.
[19] Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chung-Chi Tsai, and Chia Wen Lin, "Banet: Blur-aware attention networks for dynamic scene deblurring," arXiv preprint arXiv:2101.07518, 2021.
[20] Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean, "Distilling the knowledge in a neural network," in NIPS Deep Learning and Representation Learning Workshop, 2015.
[21] Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Y. Bengio, "Fitnets: Hints for thin deep nets," in Int. Conf. Learn. Represent., 2015.
[22] Yifan Liu, Ke Chen, Chris Liu, Zengchang Qin, Zhenbo Luo, and Jingdong Wang, "Structured knowledge distillation for semantic segmentation," in IEEE Conf. Comput. Vis. Pattern Recog., 2019. [23] Tao Wang, Li Yuan, Xiaopeng Zhang, and Jiashi Feng, "Distilling object detectors with fine-grained feature imitation," in IEEE Conf. Comput. Vis. Pattern Recog., 2019.
[24] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. International Journal of Computer Vision, 111(1), 98-136, 2015
[25] Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang, "The unreasonable effectiveness of deep features as a perceptual metric," in IEEE Conf. Comput. Vis. Pattern Recog., 2018.		zh_TW
dc.identifier.doi (DOI) 10.6814/NCCU202101688en_US