Image manipulation is a key computer vision task, aiming at：
1、the restoration of degraded image content 图像退化修复
Image Restoration is a family of inverse problems for obtaining a high quality image from a corrupted input image. Corruption may occur due to the image-capture process (e.g., noise, lens blur), post-processing (e.g., JPEG compression), or photography in non-ideal conditions (e.g., haze雾, motion blur).
2、the filling in of missing information 图像缺失修复
-
依据context信息“猜测”
-
text-guided“创作”
- 利用预先隐写的信息“重构” ？？属于这个分类吗 latent code??
3、the needed transformation and/or manipulation to achieve a desired target (with respect to perceptual quality, contents, or performance of apps working on such images)所需的转换和/或操作，以达到预期的目标(关于感知质量，内容，或应用程序的表现这样的图像)
- 局部image editing
- scene graph-based image manipulation 基于场景图的图像修改
- 图像风格转style transfer
4、“无中生有”生成图像，biggan /stargan/cyclegan