Single image super resolution
In the field of computer vision, super resolution with deep learning is a promising field that has generated multiple research, and has seen its application far and wide. In single image super resolution, the image can either be upscaled before being input into the network (pre upscaling) and its fe...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/163340 |
| _version_ | 1824454972502179840 |
|---|---|
| author | Chan, Jeremiah Sheng En |
| author2 | Chen Change Loy |
| author_facet | Chen Change Loy Chan, Jeremiah Sheng En |
| author_sort | Chan, Jeremiah Sheng En |
| collection | NTU |
| description | In the field of computer vision, super resolution with deep learning is a promising field that has generated multiple research, and has seen its application far and wide. In single image super resolution, the image can either be upscaled before being input into the network (pre upscaling) and its features learned, or it can be upscaled after the network has learned its feature (post upscaling). As with any deep learning models, the inputs into the model can affect the outputs produced. Hence, the goal of this project is to find out how much we can improve a super resolution model by filtering the inputs using a classification model. In this report, we will be discussing our analysis of the data, methodology and models used for classification/super resolution, and the results produced from our experiments. We will also be discussing some of the limitations of the project and future work regarding this project. |
| first_indexed | 2025-02-19T03:30:48Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/163340 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:30:48Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1633402022-12-05T00:40:02Z Single image super resolution Chan, Jeremiah Sheng En Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision In the field of computer vision, super resolution with deep learning is a promising field that has generated multiple research, and has seen its application far and wide. In single image super resolution, the image can either be upscaled before being input into the network (pre upscaling) and its features learned, or it can be upscaled after the network has learned its feature (post upscaling). As with any deep learning models, the inputs into the model can affect the outputs produced. Hence, the goal of this project is to find out how much we can improve a super resolution model by filtering the inputs using a classification model. In this report, we will be discussing our analysis of the data, methodology and models used for classification/super resolution, and the results produced from our experiments. We will also be discussing some of the limitations of the project and future work regarding this project. Bachelor of Engineering (Computer Science) 2022-12-05T00:40:02Z 2022-12-05T00:40:02Z 2022 Final Year Project (FYP) Chan, J. S. E. (2022). Single image super resolution. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/163340 https://hdl.handle.net/10356/163340 en SCSE21-0823 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Chan, Jeremiah Sheng En Single image super resolution |
| title | Single image super resolution |
| title_full | Single image super resolution |
| title_fullStr | Single image super resolution |
| title_full_unstemmed | Single image super resolution |
| title_short | Single image super resolution |
| title_sort | single image super resolution |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/163340 |
| work_keys_str_mv | AT chanjeremiahshengen singleimagesuperresolution |