Generative neural networks for sky image outpainting
| Thesis title in Czech: | Generativní neuronové sítě pro dokreslování obrazu oblohy |
|---|---|
| Thesis title in English: | Generative neural networks for sky image outpainting |
| Key words: | image transformer|obrazy oblohy|dokreslování |
| English key words: | image transfomer|sky imagery|outpainting |
| Academic year of topic announcement: | 2022/2023 |
| Thesis type: | Bachelor's thesis |
| Thesis language: | angličtina |
| Department: | Department of Software and Computer Science Education (32-KSVI) |
| Supervisor: | doc. RNDr. Elena Šikudová, Ph.D. |
| Author: | Bc. Matěj Mrázek - assigned and confirmed by the Study Dept. |
| Date of registration: | 19.04.2023 |
| Date of assignment: | 19.04.2023 |
| Confirmed by Study dept. on: | 02.05.2023 |
| Date and time of defence: | 29.06.2023 09:00 |
| Date of electronic submission: | 11.05.2023 |
| Date of submission of printed version: | 11.05.2023 |
| Date of proceeded defence: | 29.06.2023 |
| Opponents: | Mgr. Martin Mirbauer |
| Guidelines |
| Using neural networks, the task is to create an algorithm that expands an image beyond its borders. Use the masked generative image transformer (MaskGIT) to expand the image in low resolution, then upscale and sharpen it using diffusion models. |
| References |
| Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, William T. Freeman; MaskGIT: Masked Generative Image Transformer
Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu; Neural Discrete Representation Learning Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J. Fleet, Mohammad Norouzi; Image Super-Resolution via Iterative Refinement |