Guided Image Generation with Conditional Invertible Neural Networks
This work addresses image generation for computer vision applications, offering a novel method that improves diversity and sharpness compared to existing approaches like cGANs and VAEs.
The authors tackled guided image generation by introducing conditional invertible neural networks (cINNs), which avoid mode collapse and produce sharp images, as demonstrated on MNIST digit generation and image colorization tasks.
In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features. All parameters of the cINN are jointly optimized with a stable, maximum likelihood-based training procedure. By construction, the cINN does not experience mode collapse and generates diverse samples, in contrast to e.g. cGANs. At the same time our model produces sharp images since no reconstruction loss is required, in contrast to e.g. VAEs. We demonstrate these properties for the tasks of MNIST digit generation and image colorization. Furthermore, we take advantage of our bi-directional cINN architecture to explore and manipulate emergent properties of the latent space, such as changing the image style in an intuitive way.