Keywords: GAN inversion, wavelet transform
Abstract: Recent GAN inversion models focus on preserving image-specific details through various methods, e.g., generator tuning or feature mixing. While those are helpful for preserving details compared to naive low-rate latent inversion, they still fail to maintain high-frequency features precisely. In this paper, we point out that existing GAN inversion models have inherent limitations in both structural and training aspects, which preclude the delicate reconstruction of high-frequency features. Especially, we prove that the widely-used loss term in GAN inversion, i.e., is biased to mainly reconstructing low-frequency features. To overcome this problem, we propose a novel GAN inversion model, coined WaGI, which enables handling high-frequency features explicitly, by using a novel wavelet-based loss term and a newly proposed wavelet fusion scheme. To the best of our knowledge, WaGI is the first approach to interpret GAN inversion in the frequency domain. We demonstrate that WaGI shows outstanding results on both inversion and editing, compared to existing state-of-the-art GAN inversion models. Especially, WaGI robustly preserves high-frequency features of images even in the editing scenario. We will release our code with the pre-trained model after the review.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Generative models