A study of video denoising based on deep learning
Video denoising is a fundamental low-level vision task which means videos corrupted by noise are restored and high-quality videos are obtained. With deep learning techniques applied in the computer vision area, models based on deep neural network began to replace traditional algorithms. In this d...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180018 |
| _version_ | 1826128490177495040 |
|---|---|
| author | Zou, Dejian |
| author2 | Wen Bihan |
| author_facet | Wen Bihan Zou, Dejian |
| author_sort | Zou, Dejian |
| collection | NTU |
| description | Video denoising is a fundamental low-level vision task which means videos corrupted
by noise are restored and high-quality videos are obtained. With deep
learning techniques applied in the computer vision area, models based on deep
neural network began to replace traditional algorithms. In this dissertation, how
video denoising techniques developed in the past few years and other related
knowledge are summarized after browsing a large amount of literature. Then
two supervised methods (DVDnet and PaCNet) and two unsupervised methods
(RFR and UDVD) are explained and illustrated. To evaluate their ability to remove
AWGN, benchmarks DVAIS and Set8 are used. Then DVDnet which is
the best considering both denoised results and running time is chosen for further
experiments. A self-collected low-light dataset NIGHT and a realistic noise
dataset CRVD are used to test the generalization ability of DVDnet. Quantitative
and visual results indicate that DVDnet has remarkable denoising performance
and acceptable generalization ability. |
| first_indexed | 2024-10-01T07:25:47Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/180018 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:25:47Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1800182024-09-13T15:44:19Z A study of video denoising based on deep learning Zou, Dejian Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Computer and Information Science Engineering Video denoising Deep learning Video denoising is a fundamental low-level vision task which means videos corrupted by noise are restored and high-quality videos are obtained. With deep learning techniques applied in the computer vision area, models based on deep neural network began to replace traditional algorithms. In this dissertation, how video denoising techniques developed in the past few years and other related knowledge are summarized after browsing a large amount of literature. Then two supervised methods (DVDnet and PaCNet) and two unsupervised methods (RFR and UDVD) are explained and illustrated. To evaluate their ability to remove AWGN, benchmarks DVAIS and Set8 are used. Then DVDnet which is the best considering both denoised results and running time is chosen for further experiments. A self-collected low-light dataset NIGHT and a realistic noise dataset CRVD are used to test the generalization ability of DVDnet. Quantitative and visual results indicate that DVDnet has remarkable denoising performance and acceptable generalization ability. Master's degree 2024-09-10T01:45:25Z 2024-09-10T01:45:25Z 2024 Thesis-Master by Coursework Zou, D. (2024). A study of video denoising based on deep learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/180018 https://hdl.handle.net/10356/180018 en application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Engineering Video denoising Deep learning Zou, Dejian A study of video denoising based on deep learning |
| title | A study of video denoising based on deep learning |
| title_full | A study of video denoising based on deep learning |
| title_fullStr | A study of video denoising based on deep learning |
| title_full_unstemmed | A study of video denoising based on deep learning |
| title_short | A study of video denoising based on deep learning |
| title_sort | study of video denoising based on deep learning |
| topic | Computer and Information Science Engineering Video denoising Deep learning |
| url | https://hdl.handle.net/10356/180018 |
| work_keys_str_mv | AT zoudejian astudyofvideodenoisingbasedondeeplearning AT zoudejian studyofvideodenoisingbasedondeeplearning |