# RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution

arXiv: https://arxiv.org/abs/2603.12493 · HTML: https://mlsanity.com/paper/2603.12493/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 52 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 35)

- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks](https://mlsanity.com/paper/1809.00437/) (2018)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [A Deep Journey into Super-resolution: A survey](https://mlsanity.com/paper/1904.07523/) (2019)
- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021)
- [Rethinking Noise Synthesis and Modeling in Raw Denoising](https://mlsanity.com/paper/2110.04756/) (2021)
- [Camera Lens Super-Resolution](https://mlsanity.com/paper/1904.03378/) (2019)
- [Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution](https://mlsanity.com/paper/2108.05302/) (2021)
- [Towards Real Scene Super-Resolution with Raw Images](https://mlsanity.com/paper/1905.12156/) (2019)
- [Dirty Pixels: Towards End-to-End Image Processing and Perception](https://mlsanity.com/paper/1701.06487/) (2017)
- [CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks](https://mlsanity.com/paper/2006.12709/) (2020)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [Learning the Degradation Distribution for Blind Image Super-Resolution](https://mlsanity.com/paper/2203.04962/) (2022)
- [Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata](https://mlsanity.com/paper/2206.01813/) (2022)
- [Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution](https://mlsanity.com/paper/2305.18107/) (2023)
- [High Dynamic Range and Super-Resolution from Raw Image Bursts](https://mlsanity.com/paper/2207.14671/) (2022)

## Abstract (arXiv)

Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.