# Robust Super-Resolution GAN, with Manifold-based and Perception Loss

arXiv: https://arxiv.org/abs/1903.06920 · HTML: https://mlsanity.com/paper/1903.06920/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2019.

## Built on by (most cited first, 15 of 15)

- [Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions](https://mlsanity.com/paper/2101.09113/) (2021)
- [BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks](https://mlsanity.com/paper/2207.06873/) (2022)
- [Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data](https://mlsanity.com/paper/2107.09892/) (2021)
- [Uncertainty-Guided Progressive GANs for Medical Image Translation](https://mlsanity.com/paper/2106.15542/) (2021)
- [Robustness via Uncertainty-aware Cycle Consistency](https://mlsanity.com/paper/2110.12467/) (2021)
- [Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement](https://mlsanity.com/paper/2110.03343/) (2021)
- [A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement](https://mlsanity.com/paper/2106.15575/) (2021)
- [Reconstructing High-resolution Turbulent Flows Using Physics-Guided Neural Networks](https://mlsanity.com/paper/2109.03327/) (2021)
- [USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution](https://mlsanity.com/paper/2305.17520/) (2023)
- [Super resolution of histopathological frozen sections via deep learning preserving tissue structure](https://mlsanity.com/paper/2310.11112/) (2023)
- [Physics-enhanced Neural Operator for Simulating Turbulent Transport](https://mlsanity.com/paper/2406.04367/) (2024)
- [Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models](https://mlsanity.com/paper/2211.06250/) (2022)
- [Reconstructing Turbulent Flows Using Physics-Aware Spatio-Temporal Dynamics and Test-Time Refinement](https://mlsanity.com/paper/2304.12130/) (2023)
- [Modeling Continuous Spatial-temporal Dynamics of Turbulent Flow with Test-time Refinement](https://mlsanity.com/paper/2412.19927/) (2024)
- [BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography](https://mlsanity.com/paper/2510.20029/) (2025)

## Abstract (arXiv)

Super-resolution using deep neural networks typically relies on highly curated training sets that are often unavailable in clinical deployment scenarios. Using loss functions that assume Gaussian-distributed residuals makes the learning sensitive to corruptions in clinical training sets. We propose novel loss functions that are robust to corruptions in training sets by modeling heavy-tailed non-Gaussian distributions on the residuals. We propose a loss based on an autoencoder-based manifold-distance between the super-resolved and high-resolution images, to reproduce realistic textural content in super-resolved images. We propose to learn to super-resolve images to match human perceptions of structure, luminance, and contrast. Results on a large clinical dataset shows the advantages of each of our contributions, where our framework improves over the state of the art.