Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2003.08791 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909831702511616 |
|---|---|
| author | Anokhin, Ivan Solovev, Pavel Korzhenkov, Denis Kharlamov, Alexey Khakhulin, Taras Silvestrov, Alexey Nikolenko, Sergey Lempitsky, Victor Sterkin, Gleb |
| author_facet | Anokhin, Ivan Solovev, Pavel Korzhenkov, Denis Kharlamov, Alexey Khakhulin, Taras Silvestrov, Alexey Nikolenko, Sergey Lempitsky, Victor Sterkin, Gleb |
| contents | Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (HiDT) model for this task. HiDT combines a generative image-to-image model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics and human evaluation. Importantly, this good performance comes as a result of training on a dataset of still landscape images with no daytime labels available. Our results are available at https://saic-mdal.github.io/HiDT/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2003_08791 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | High-Resolution Daytime Translation Without Domain Labels Anokhin, Ivan Solovev, Pavel Korzhenkov, Denis Kharlamov, Alexey Khakhulin, Taras Silvestrov, Alexey Nikolenko, Sergey Lempitsky, Victor Sterkin, Gleb Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (HiDT) model for this task. HiDT combines a generative image-to-image model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics and human evaluation. Importantly, this good performance comes as a result of training on a dataset of still landscape images with no daytime labels available. Our results are available at https://saic-mdal.github.io/HiDT/. |
| title | High-Resolution Daytime Translation Without Domain Labels |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2003.08791 |