The task of upscaling pictures is very ill-posed since it requires the creation of novel data. Any algorithm or model trying to perform this task will have to interpolate and guess the missing pixels in the pictures. Classical algorithms usually result in blurred or pixelated interpolations, especially visible around sharp edges. The reason it could be considered a good idea to use neural networks to upscale pictures is because they can infer context when upsampling different parts of an image. In this report, a special deep learning structure called U-Net is trained on reconstructing high-resolution images from the Div2k dataset. Multiple loss functions are tested and a combination of a GAN-based loss function, simple pixel loss and also a Sobel-based edge loss was used to get the best results. The proposed model scored a PSNR score of 33.11dB compared to Lanczos 30.23dB, one of the best classical algorithms, on the validation dataset.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:uu-445567 |
| Date | January 2021 |
| Creators | Norée Palm, Caspar, Granström, Hugo |
| Publisher | Uppsala universitet, Avdelningen för visuell information och interaktion, Uppsala universitet, Avdelningen för visuell information och interaktion |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | MATVET-F ; 21028 |
Page generated in 0.0032 seconds