Making Images from Images: Interleaving Denoising and Transformation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929603758522368 |
|---|---|
| author | Baluja, Shumeet Marwood, David Baluja, Ashwin |
| author_facet | Baluja, Shumeet Marwood, David Baluja, Ashwin |
| contents | Simply by rearranging the regions of an image, we can create a new image of any subject matter. The definition of regions is user definable, ranging from regularly and irregularly-shaped blocks, concentric rings, or even individual pixels. Our method extends and improves recent work in the generation of optical illusions by simultaneously learning not only the content of the images, but also the parameterized transformations required to transform the desired images into each other. By learning the image transforms, we allow any source image to be pre-specified; any existing image (e.g. the Mona Lisa) can be transformed to a novel subject. We formulate this process as a constrained optimization problem and address it through interleaving the steps of image diffusion with an energy minimization step. Unlike previous methods, increasing the number of regions actually makes the problem easier and improves results. We demonstrate our approach in both pixel and latent spaces. Creative extensions, such as using infinite copies of the source image and employing multiple source images, are also given. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15925 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Making Images from Images: Interleaving Denoising and Transformation Baluja, Shumeet Marwood, David Baluja, Ashwin Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Neural and Evolutionary Computing Simply by rearranging the regions of an image, we can create a new image of any subject matter. The definition of regions is user definable, ranging from regularly and irregularly-shaped blocks, concentric rings, or even individual pixels. Our method extends and improves recent work in the generation of optical illusions by simultaneously learning not only the content of the images, but also the parameterized transformations required to transform the desired images into each other. By learning the image transforms, we allow any source image to be pre-specified; any existing image (e.g. the Mona Lisa) can be transformed to a novel subject. We formulate this process as a constrained optimization problem and address it through interleaving the steps of image diffusion with an energy minimization step. Unlike previous methods, increasing the number of regions actually makes the problem easier and improves results. We demonstrate our approach in both pixel and latent spaces. Creative extensions, such as using infinite copies of the source image and employing multiple source images, are also given. |
| title | Making Images from Images: Interleaving Denoising and Transformation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2411.15925 |