Deep task-driven video denoising
The main contribution of this research is two folds. First, this research work explores the vast domain of video denoising, analyze challenges in designing video denoising algorithm, and study previously successful state-of-the-art video denoising techniques. Secondly, this research aims to optimize...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/138731 |
| _version_ | 1826121896957050880 |
|---|---|
| author | Kurniadi, Daniel |
| author2 | Wen Bihan |
| author_facet | Wen Bihan Kurniadi, Daniel |
| author_sort | Kurniadi, Daniel |
| collection | NTU |
| description | The main contribution of this research is two folds. First, this research work explores the vast domain of video denoising, analyze challenges in designing video denoising algorithm, and study previously successful state-of-the-art video denoising techniques. Secondly, this research aims to optimize video denoising algorithm when the result is supplied for high-level task behind it. We propose a method that features high-level information guided video denoising that capable of achieving comparable result with the state-of-the-art denoising while preserving semantic-aware details for high-level vision tasks. |
| first_indexed | 2024-10-01T05:39:39Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/138731 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:39:39Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1387312023-07-07T18:19:24Z Deep task-driven video denoising Kurniadi, Daniel Wen Bihan School of Electrical and Electronic Engineering Wen Bihan bihan.wen@ntu.edu.sg Engineering::Electrical and electronic engineering The main contribution of this research is two folds. First, this research work explores the vast domain of video denoising, analyze challenges in designing video denoising algorithm, and study previously successful state-of-the-art video denoising techniques. Secondly, this research aims to optimize video denoising algorithm when the result is supplied for high-level task behind it. We propose a method that features high-level information guided video denoising that capable of achieving comparable result with the state-of-the-art denoising while preserving semantic-aware details for high-level vision tasks. Bachelor of Engineering (Electrical and Electronic Engineering) 2020-05-12T04:58:08Z 2020-05-12T04:58:08Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138731 en A3272-191 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Kurniadi, Daniel Deep task-driven video denoising |
| title | Deep task-driven video denoising |
| title_full | Deep task-driven video denoising |
| title_fullStr | Deep task-driven video denoising |
| title_full_unstemmed | Deep task-driven video denoising |
| title_short | Deep task-driven video denoising |
| title_sort | deep task driven video denoising |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/138731 |
| work_keys_str_mv | AT kurniadidaniel deeptaskdrivenvideodenoising |