Toward a Controllable Disentanglement Network
This work addresses challenges in disentangled representation learning for image synthesis, offering incremental improvements in controllability and quality.
The paper tackles the problems of controlling disentanglement degree in image editing and balancing disentanglement with reconstruction quality, achieving improved perceptual quality and quantitative disentanglement strength through a combined autoencoder-GAN model.
This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstruction quality. To encourage disentanglement, we devise a distance covariance based decorrelation regularization. Further, for the reconstruction step, our model leverages a soft target representation combined with the latent image code. By exploring the real-valued space of the soft target representation, we are able to synthesize novel images with the designated properties. To improve the perceptual quality of images generated by autoencoder (AE)-based models, we extend the encoder-decoder architecture with the generative adversarial network (GAN) by collapsing the AE decoder and the GAN generator into one. We also design a classification based protocol to quantitatively evaluate the disentanglement strength of our model. Experimental results showcase the benefits of the proposed model.