GAN Inversion for Out-of-Range Images With Geometric Transformations

Kyoungkook Kang, Seongtae Kim, Sunghyun Cho; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13941-13949

Abstract


For successful semantic editing of real images, it is critical for a GAN inversion method to find an in-domain latent code that aligns with the domain of a pre-trained GAN model. Unfortunately, such in-domain latent codes can be found only for in-range images that align with the training images of a GAN model. In this paper, we propose BDInvert, a novel GAN inversion approach to semantic editing of out-of-range images that are geometrically unaligned with the training images of a GAN model. To find a latent code that is semantically editable, BDInvert inverts an input out-of-range image into an alternative latent space than the original latent space. We also propose a regularized inversion method to find a solution that supports semantic editing in the alternative space. Our experiments show that BDInvert effectively supports semantic editing of out-of-range images with geometric transformations.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2021_ICCV, author = {Kang, Kyoungkook and Kim, Seongtae and Cho, Sunghyun}, title = {GAN Inversion for Out-of-Range Images With Geometric Transformations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {13941-13949} }