Force-in-domain GAN inversion

TL;DR

This paper introduces a force-in-domain GAN that improves the accuracy of GAN inversion by ensuring the inverted code remains within the latent space, enhancing image reconstruction and semantic editing capabilities.

Contribution

It proposes a novel force-in-domain GAN that uses a discriminator to keep the inverted code within the latent space, addressing deviations in existing in-domain GAN inversion methods.

Findings

Improved pixel-level image reconstruction.

Better alignment of inverted codes with the latent space.

Enhanced semantic editing performance.

Abstract

Empirical works suggest that various semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to generate images. To perform real image editing, it requires an accurate mapping from the real image to the latent space to leveraging these learned semantics, which is important yet difficult. An in-domain GAN inversion approach is recently proposed to constraint the inverted code within the latent space by forcing the reconstructed image obtained from the inverted code within the real image space. Empirically, we find that the inverted code by the in-domain GAN can deviate from the latent space significantly. To solve this problem, we propose a force-in-domain GAN based on the in-domain GAN, which utilizes a discriminator to force the inverted code within the latent space. The force-in-domain GAN can also be interpreted by a cycle-GAN with slight modification. Extensive experiments show that our force-in-domain GAN not only reconstructs the target image at the pixel level, but also align the inverted code with the latent space well for semantic editing.