One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
This work addresses the need for efficient and generalizable image reconstruction in computer vision, though it appears incremental as it builds on existing StyleGAN architecture.
The paper tackles the problem of reconstructing images across multiple domains using a novel StyleGAN-based autoencoder, achieving up to 40 images per second on a single GPU, which is 28x faster than previous approaches, and shows competitive results in image denoising.
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images into specific GAN architectures to reconstruct the original images. We present a novel StyleGAN-based autoencoder architecture, which can reconstruct images with very high quality across several data domains. We demonstrate a previously unknown grade of generalizablility by training the encoder and decoder independently and on different datasets. Furthermore, we provide new insights about the significance and capabilities of noise inputs of the well-known StyleGAN architecture. Our proposed architecture can handle up to 40 images per second on a single GPU, which is approximately 28x faster than previous approaches. Finally, our model also shows promising results, when compared to the state-of-the-art on the image denoising task, although it was not explicitly designed for this task.