Generative models for multi-modality image inpainting and resolution enhancement
| dc.contributor.advisor | Ebrahimi, Mehran | |
| dc.contributor.author | Abed jooy Divshali, Aref | |
| dc.date.accessioned | 2022-04-26T15:37:43Z | |
| dc.date.accessioned | 2022-06-15T15:31:35Z | |
| dc.date.available | 2022-04-26T15:37:43Z | |
| dc.date.available | 2022-06-15T15:31:35Z | |
| dc.date.issued | 2022-04-01 | |
| dc.degree.discipline | Computer Science | en |
| dc.degree.level | Master of Science (MSc) | en |
| dc.description.abstract | Recently, deep learning methods specifically generative adversarial networks (GANs) have been used to rapidly improve a wide range of image enhancement tasks including image inpainting and image resolution enhancement also known as super-resolution. Image-to-image translation methods convert an image provided in a source modality (e.g., a nighttime image) to an image of a target modality (e.g., a daytime image) by learning an image generation function. These methods can be applied to a wide variety of problems in image processing and computer vision. The use of GANs for image-to-image translation has also been extensively studied. We propose the problem of combining the image-enhancement tasks (e.g., image inpainting or super-resolution) with the image-to-image translation task in a joint formulation. Given a distorted nighttime image of a scene can one recover a restored daytime image of the same scene? Two models to address the joint problem will be presented. Our models are validated on night-to-day joint image translation and enhancement for both super-resolution and inpainting. Promising qualitative and quantitative results will be reported. | en |
| dc.description.sponsorship | University of Ontario Institute of Technology | en |
| dc.identifier.uri | https://hdl.handle.net/10155/1437 | |
| dc.language.iso | en | en |
| dc.subject | Image inpainting | en |
| dc.subject | Image-to-image translation | en |
| dc.subject | Image super-resolution | en |
| dc.subject | Generative Adversarial Network (GAN) | en |
| dc.title | Generative models for multi-modality image inpainting and resolution enhancement | en |
| dc.type | Thesis | en |