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

Taewon Kang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 3515-3522

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 Frechet 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Kang_2021_ICCV, author = {Kang, Taewon}, title = {Multiple GAN Inversion for Exemplar-Based Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {3515-3522} }