[1906.05284] Image-Adaptive GAN based Reconstruction

Electrical Engineering and Systems Science > Image and Video Processing arXiv:1906.05284 (eess) [Submitted on 12 Jun 2019 (v1), last revised 30 Mar 2026 (this version, v3)] Title:Image-Adaptive GAN based Reconstruction Authors:Shady Abu Hussein, Tom Tirer, Raja Giryes View a PDF of the paper titled Image-Adaptive GAN based Reconstruction, by Shady Abu Hussein and 1 other authors View PDF HTML (experimental) Abstract: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. Comments: Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv:1906.05284 [eess.IV]   (or arXiv:1906.05284v3 [eess.IV] for this version)   https://doi.org/10.48550/arXiv.1906.05284 F...