TRABALHOS DE FIM DE CURSO @PUC-Rio
| Título: | SINGLE IMAGE SUPER-RESOLUTION, A COMPARATIVE STUDY | ||||||||||||
| Autor(es): |
YAN MARTINS BRAZ GUREVITZ CUNHA |
||||||||||||
| Colaborador(es): |
MARCO SERPA MOLINARO - Orientador |
||||||||||||
| Catalogação: | 09/SET/2021 | Língua(s): | PORTUGUESE - BRAZIL |
||||||||||
| Tipo: | TEXT | Subtipo: | SENIOR PROJECT | ||||||||||
| Notas: |
[pt] Todos os dados constantes dos documentos são de inteira responsabilidade de seus autores. Os dados utilizados nas descrições dos documentos estão em conformidade com os sistemas da administração da PUC-Rio. [en] All data contained in the documents are the sole responsibility of the authors. The data used in the descriptions of the documents are in conformity with the systems of the administration of PUC-Rio. |
||||||||||||
| Referência(s): |
[pt] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/TFCs/consultas/conteudo.php?strSecao=resultado&nrSeq=54583@1 [en] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/TFCs/consultas/conteudo.php?strSecao=resultado&nrSeq=54583@2 |
||||||||||||
| DOI: | https://doi.org/10.17771/PUCRio.acad.54583 | ||||||||||||
| Resumo: | |||||||||||||
|
The Single Image Super-Resolution (SISR) problem consists of trying to obtain a High-Resolution version of an image from its Low-Resolution version, a quite challenging task. Recently Neural Networks models have shown to be quite powerful in solving this problem. This project will cover a broad study of state-of-the-art
solutions to this problem, and analyse in detail three of the best current models: SRResNet , EDSR and WDSR. Each of these models will go through computational tests to revalidate their performance, utilising various metrics to compare the generated images with the ground truth (High-Resolution original). We ll study the
difference in architecture between the models and what causes the difference in performance.
|
|||||||||||||
|
|||||||||||||