Spatially-Adaptive Pixelwise Networks for Fast Image Translation
| Autor: | Tomer Michaeli, Michaël Gharbi, Richard Zhang, Tamar Rott Shaham, Eli Shechtman |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Speedup Pixel business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Translation (geometry) Spatial reference system Image translation Artificial intelligence Affine transformation business Algorithm Image resolution Generator (mathematics) |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr46437.2021.01464 |
| Popis: | We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function of the full-resolution image. In fact, we use pixel-wise networks; that is, each pixel is processed independently of others, through a composition of simple affine transformations and nonlinearities. We take three important steps to equip such a seemingly simple function with adequate expressivity. First, the parameters of the pixel-wise networks are spatially varying, so they can represent a broader function class than simple 1 × 1 convolutions. Second, these parameters are predicted by a fast convolutional network that processes an aggressively low-resolution representation of the input. Third, we augment the input image by concatenating a sinusoidal encoding of spatial coordinates, which provides an effective inductive bias for generating realistic novel high-frequency image content. As a result, our model is up to 18× faster than state-of-the-art baselines. We achieve this speedup while generating comparable visual quality across different image resolutions and translation domains. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|