Learning Images Across Scales Using Adversarial Training
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914833655398400 |
|---|---|
| author | Wolski, Krzysztof Djeacoumar, Adarsh Javanmardi, Alireza Seidel, Hans-Peter Theobalt, Christian Cordonnier, Guillaume Myszkowski, Karol Drettakis, George Pan, Xingang Leimkühler, Thomas |
| author_facet | Wolski, Krzysztof Djeacoumar, Adarsh Javanmardi, Alireza Seidel, Hans-Peter Theobalt, Christian Cordonnier, Guillaume Myszkowski, Karol Drettakis, George Pan, Xingang Leimkühler, Thomas |
| contents | The real world exhibits rich structure and detail across many scales of observation. It is difficult, however, to capture and represent a broad spectrum of scales using ordinary images. We devise a novel paradigm for learning a representation that captures an orders-of-magnitude variety of scales from an unstructured collection of ordinary images. We treat this collection as a distribution of scale-space slices to be learned using adversarial training, and additionally enforce coherency across slices. Our approach relies on a multiscale generator with carefully injected procedural frequency content, which allows to interactively explore the emerging continuous scale space. Training across vastly different scales poses challenges regarding stability, which we tackle using a supervision scheme that involves careful sampling of scales. We show that our generator can be used as a multiscale generative model, and for reconstructions of scale spaces from unstructured patches. Significantly outperforming the state of the art, we demonstrate zoom-in factors of up to 256x at high quality and scale consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08924 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Images Across Scales Using Adversarial Training Wolski, Krzysztof Djeacoumar, Adarsh Javanmardi, Alireza Seidel, Hans-Peter Theobalt, Christian Cordonnier, Guillaume Myszkowski, Karol Drettakis, George Pan, Xingang Leimkühler, Thomas Graphics Computer Vision and Pattern Recognition Machine Learning The real world exhibits rich structure and detail across many scales of observation. It is difficult, however, to capture and represent a broad spectrum of scales using ordinary images. We devise a novel paradigm for learning a representation that captures an orders-of-magnitude variety of scales from an unstructured collection of ordinary images. We treat this collection as a distribution of scale-space slices to be learned using adversarial training, and additionally enforce coherency across slices. Our approach relies on a multiscale generator with carefully injected procedural frequency content, which allows to interactively explore the emerging continuous scale space. Training across vastly different scales poses challenges regarding stability, which we tackle using a supervision scheme that involves careful sampling of scales. We show that our generator can be used as a multiscale generative model, and for reconstructions of scale spaces from unstructured patches. Significantly outperforming the state of the art, we demonstrate zoom-in factors of up to 256x at high quality and scale consistency. |
| title | Learning Images Across Scales Using Adversarial Training |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.08924 |