Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
This work addresses the problem of photorealistic image manipulation for applications like face editing, though it is incremental as it builds on the PIONEER model.
The paper tackles the challenge of achieving fast encoding, faithful reconstructions, sharp high-resolution samples, and a well-structured latent space for semantic image manipulation in generative autoencoders, improving face identity conservation in CelebAHQ and achieving state-of-the-art disentanglement performance.
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs. There are no current autoencoder or GAN models that satisfactorily achieve all of these. We build on the progressively growing autoencoder model PIONEER, for which we completely alter the training dynamics based on a careful analysis of recently introduced normalization schemes. We show significantly improved visual and quantitative results for face identity conservation in CelebAHQ. Our model achieves state-of-the-art disentanglement of latent space, both quantitatively and via realistic image attribute manipulations. On the LSUN Bedrooms dataset, we improve the disentanglement performance of the vanilla PIONEER, despite having a simpler model. Overall, our results indicate that the PIONEER networks provide a way towards photorealistic face manipulation.