Log In Sign Up

Guided Image Generation with Conditional Invertible Neural Networks

by   Lynton Ardizzone, et al.

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.


page 1

page 5

page 8

page 9


Conditional Invertible Neural Networks for Diverse Image-to-Image Translation

We introduce a new architecture called a conditional invertible neural n...

The Neural Painter: Multi-Turn Image Generation

In this work we combine two research threads from Vision/ Graphics and N...

PAGER: Progressive Attribute-Guided Extendable Robust Image Generation

This work presents a generative modeling approach based on successive su...

Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory

Episodic and semantic memory are critical components of the human memory...

Spatially Multi-conditional Image Generation

In most scenarios, conditional image generation can be thought of as an ...

DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation

In this work, we consider the task of generating highly-realistic images...

Transform the Set: Memory Attentive Generation of Guided and Unguided Image Collages

Cutting and pasting image segments feels intuitive: the choice of source...

Code Repositories


Code for the paper "Guided Image Generation with Conditional Invertible Neural Networks" (2019)

view repo


Framework for Easily Invertible Architectures

view repo


Conditional Generative model (Normalizing Flow) and experimenting style transfer using this model

view repo