mlsanityData to 14 Oct 2026

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

arXiv 2105.02104 ↗First posted 5 May 2021cs.CV cs.AIcited by 24

Not on the map. Why?

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.

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

27 of 37 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2016Density estimation using Real NVPcited by 2,042
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  12. 2016Colorful Image Colorizationcited by 1,114
15 more
  1. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  2. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  3. 2017Toward Multimodal Image-to-Image Translationcited by 296
  4. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  5. 2015A note on the evaluation of generative modelscited by 292
  6. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
  7. 2018i-RevNet: Deep Invertible Networkscited by 137
  8. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 92
  9. 2019Integer Discrete Flows and Lossless Compressioncited by 83
  10. 2018Excessive Invariance Causes Adversarial Vulnerabilitycited by 66
  11. 2016Learning Diverse Image Colorizationcited by 43
  12. 2019Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicalitycited by 31
  13. 2017It Takes (Only) Two: Adversarial Generator-Encoder Networkscited by 19
  14. 2019DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfercited by 19
  15. 2020Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 6; 2024: 2; 2025: 2; 2026: 4.

24 papers.

Sort:

By area:

  1. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  2. 2021Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpointcited by 32
  3. 2023Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernelcited by 25
  4. 2021Generalized Normalizing Flows via Markov Chainscited by 23
  5. 2022Conditional Injective Flows for Bayesian Imagingcited by 13
  6. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 13
  7. 2023AmbientFlow: Invertible generative models from incomplete, noisy measurementscited by 11
  8. 2022WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolutioncited by 10
  9. 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imagingcited by 10
  10. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  11. 2022Invertible Neural Networks for Graph Predictioncited by 6
  12. 2022Distilling Style from Image Pairs for Global Forward and Inverse Tone Mappingcited by 5
12 more
  1. 2022Tackling Multimodal Device Distributions in Inverse Photonic Design using Invertible Neural Networkscited by 3
  2. 2025AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perceptioncited by 3
  3. 2026How well do generative models solve inverse problems? A benchmark studycited by 3
  4. 2021RID-Noise: Towards Robust Inverse Design under Noisy Environmentscited by 2
  5. 2022Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networkscited by 2
  6. 2024ISR: Invertible Symbolic Regressioncited by 2
  7. 2026From Mice to Trains: Amortized Bayesian Inference on Graph Datacited by 2
  8. 2024Optimizing Retinal Prosthetic Stimuli with Conditional Invertible Neural Networkscited by 1
  9. 2023PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flowcited by 0
  10. 2023Application-driven Validation of Posteriors in Inverse Problemscited by 0
  11. 2026Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectracited by 0
  12. 2026MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventionscited by 0