Multiple GAN Inversion for Exemplar-based Image-to-Image Translation

TL;DR

This paper introduces a novel Multiple GAN Inversion method for exemplar-based image-to-image translation that automatically selects the best image reconstruction without human intervention, improving generalization and alignment issues.

Contribution

The proposed method uses a self-deciding algorithm based on FID to select the best reconstruction, overcoming limitations of existing aligned-input and generalization issues.

Findings

Outperforms existing exemplar-based translation methods

Automatically selects optimal layers without training or supervision

Enhances translation quality for unseen images

Abstract

Existing state-of-the-art techniques in exemplar-based image-to-image translation hold several critical concerns. Existing methods related to exemplar-based image-to-image translation are impossible to translate on an image tuple input (source, target) that is not aligned. Additionally, we can confirm that the existing method exhibits limited generalization ability to unseen images. In order to overcome this limitation, we propose Multiple GAN Inversion for Exemplar-based Image-to-Image Translation. Our novel Multiple GAN Inversion avoids human intervention by using a self-deciding algorithm to choose the number of layers using Fr\'echet Inception Distance(FID), which selects more plausible image reconstruction results among multiple hypotheses without any training or supervision. Experimental results have in fact, shown the advantage of the proposed method compared to existing state-of-the-art exemplar-based image-to-image translation methods.