dc.contributor.author |
Morshed, Mashrur Mahmud |
|
dc.contributor.author |
Iqbal, Hasan Tanvir |
|
dc.contributor.author |
Rishad, Mazharul Islam |
|
dc.date.accessioned |
2022-03-25T09:40:27Z |
|
dc.date.available |
2022-03-25T09:40:27Z |
|
dc.date.issued |
2021-03-30 |
|
dc.identifier.uri |
http://hdl.handle.net/123456789/1287 |
|
dc.description |
Supervised by
Mr. Hasan Mahmud,
Department of Computer Science and Engineering(CSE),
Islamic University of Technology(IUT),
Board Bazar, Gazipur-1704, Bangladesh |
en_US |
dc.description.abstract |
Image to image translation is a highly generalized learning task, that canbe applied to a wide number of Computer Vision application domains. Condi-tional Generative Adversarial Networks (cGANs) are used to perform image toimage translation. The generator network typically used in the existing cGANapproach, Pix2Pix, adopts the U-Net architecture, consisting of encoding anddecoding convolutional layers and skip-connections between layers of the sameresolution. While effective and convenient, such an arrangement is also restrictivein some ways, as the feature reconstruction process in the decoder cannot utilizemulti-scale features. In our work, we study a generator architecture where featuremaps are propagated to the decoder from different resolution levels. We’ve exper-imentally shown improved performance on two different datasets — the NYU-V2depth dataset and the Labels2Facades dataset. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh |
en_US |
dc.title |
Image to Image Translation With Multi- Scale Generator |
en_US |
dc.type |
Thesis |
en_US |