Image-Adaptive GAN based Reconstruction
This work addresses the problem of improving image reconstruction quality for complex classes like human faces in inverse imaging problems, representing an incremental advancement over existing methods.
The paper tackled the limited representation capabilities of pre-trained generative models in capturing complex image distributions, such as human faces, by proposing an image-adaptive GAN approach with back-projections for compliance with observations, resulting in empirical advantages demonstrated for image super-resolution and compressed sensing tasks.
In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods still do not capture the full distribution for complex classes of images, such as human faces. This deficiency has been clearly observed in previous works that use pre-trained generative models to solve imaging inverse problems. In this paper, we suggest to mitigate the limited representation capabilities of generators by making them image-adaptive and enforcing compliance of the restoration with the observations via back-projections. We empirically demonstrate the advantages of our proposed approach for image super-resolution and compressed sensing.