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

arXiv: https://arxiv.org/abs/2105.02104 · HTML: https://mlsanity.com/paper/2105.02104/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 5 May 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)](https://mlsanity.com/paper/2001.04872/) (2020)
- [Integer Discrete Flows and Lossless Compression](https://mlsanity.com/paper/1905.07376/) (2019)
- [Excessive Invariance Causes Adversarial Vulnerability](https://mlsanity.com/paper/1811.00401/) (2018)
- [Learning Diverse Image Colorization](https://mlsanity.com/paper/1612.01958/) (2016)
- [Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality](https://mlsanity.com/paper/1906.02994/) (2019)
- [It Takes (Only) Two: Adversarial Generator-Encoder Networks](https://mlsanity.com/paper/1704.02304/) (2017)
- [DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer](https://mlsanity.com/paper/1908.08074/) (2019)
- [Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification](https://mlsanity.com/paper/2001.06448/) (2020)

## Built on by (most cited first, 24 of 24)

- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint](https://mlsanity.com/paper/2109.11375/) (2021)
- [Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel](https://mlsanity.com/paper/2310.03054/) (2023)
- [Generalized Normalizing Flows via Markov Chains](https://mlsanity.com/paper/2111.12506/) (2021)
- [Conditional Injective Flows for Bayesian Imaging](https://mlsanity.com/paper/2204.07664/) (2022)
- [A Review of Change of Variable Formulas for Generative Modeling](https://mlsanity.com/paper/2308.02652/) (2023)
- [AmbientFlow: Invertible generative models from incomplete, noisy measurements](https://mlsanity.com/paper/2309.04856/) (2023)
- [WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution](https://mlsanity.com/paper/2201.08157/) (2022)
- [A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging](https://mlsanity.com/paper/2306.01630/) (2023)
- [Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluation](https://mlsanity.com/paper/2502.04949/) (2025)
- [Invertible Neural Networks for Graph Prediction](https://mlsanity.com/paper/2206.01163/) (2022)
- [Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping](https://mlsanity.com/paper/2209.15165/) (2022)
- [Tackling Multimodal Device Distributions in Inverse Photonic Design using Invertible Neural Networks](https://mlsanity.com/paper/2208.14212/) (2022)
- [AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perception](https://mlsanity.com/paper/2502.08374/) (2025)
- [How well do generative models solve inverse problems? A benchmark study](https://mlsanity.com/paper/2601.23238/) (2026)
- [RID-Noise: Towards Robust Inverse Design under Noisy Environments](https://mlsanity.com/paper/2112.03912/) (2021)
- [Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networks](https://mlsanity.com/paper/2210.04629/) (2022)
- [ISR: Invertible Symbolic Regression](https://mlsanity.com/paper/2405.06848/) (2024)
- [From Mice to Trains: Amortized Bayesian Inference on Graph Data](https://mlsanity.com/paper/2601.02241/) (2026)
- [Optimizing Retinal Prosthetic Stimuli with Conditional Invertible Neural Networks](https://mlsanity.com/paper/2403.04884/) (2024)
- [PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow](https://mlsanity.com/paper/2307.09146/) (2023)
- [Application-driven Validation of Posteriors in Inverse Problems](https://mlsanity.com/paper/2309.09764/) (2023)
- [Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra](https://mlsanity.com/paper/2602.03875/) (2026)
- [MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions](https://mlsanity.com/paper/2609.11253/) (2026)

## Abstract (arXiv)

We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with existing INN models due to some fundamental limitations. The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning image into maximally informative features. All parameters of a cINN are jointly optimized with a stable, maximum likelihood-based training procedure. Even though INN-based models have received far less attention in the literature than GANs, they have been shown to have some remarkable properties absent in GANs, e.g. apparent immunity to mode collapse. We find that our cINNs leverage these properties for image-to-image translation, demonstrated on day to night translation and image colorization. Furthermore, we take advantage of our bidirectional cINN architecture to explore and manipulate emergent properties of the latent space, such as changing the image style in an intuitive way.