GAN Inversion for Out-of-Range Images with Geometric Transformations
This addresses a specific bottleneck in GAN inversion for geometrically unaligned images, enabling semantic editing where previous methods fail, but it is incremental as it builds on existing GAN inversion frameworks.
The paper tackles the problem of GAN inversion for out-of-range images with geometric transformations, proposing BDInvert to find semantically editable latent codes, and shows it effectively supports semantic editing in experiments.
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.