# Towards Real Scene Super-Resolution with Raw Images

arXiv: https://arxiv.org/abs/1905.12156 · HTML: https://mlsanity.com/paper/1905.12156/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 30 of 44)

- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Investigating Tradeoffs in Real-World Video Super-Resolution](https://mlsanity.com/paper/2111.12704/) (2021)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [Text Prior Guided Scene Text Image Super-resolution](https://mlsanity.com/paper/2106.15368/) (2021)
- [3D Human Pose, Shape and Texture from Low-Resolution Images and Videos](https://mlsanity.com/paper/2103.06498/) (2021)
- [Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution](https://mlsanity.com/paper/2411.10798/) (2024)
- [Variational Deep Image Restoration](https://mlsanity.com/paper/2207.01074/) (2022)
- [GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond](https://mlsanity.com/paper/2207.14812/) (2022)
- [Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset](https://mlsanity.com/paper/2209.12475/) (2022)
- [Toward Real-World Super-Resolution via Adaptive Downsampling Models](https://mlsanity.com/paper/2109.03444/) (2021)
- [Exploiting Raw Images for Real-Scene Super-Resolution](https://mlsanity.com/paper/2102.01579/) (2021)
- [A Categorized Reflection Removal Dataset with Diverse Real-world Scenes](https://mlsanity.com/paper/2108.03380/) (2021)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Neural Camera Simulators](https://mlsanity.com/paper/2104.05237/) (2021)
- [Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot](https://mlsanity.com/paper/2111.07281/) (2021)
- [Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising](https://mlsanity.com/paper/2101.10760/) (2021)
- [NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution](https://mlsanity.com/paper/2506.02197/) (2025)
- [RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset](https://mlsanity.com/paper/2305.00767/) (2023)
- [Data Acquisition and Preparation for Dual-reference Deep Learning of Image Super-Resolution](https://mlsanity.com/paper/2108.02348/) (2021)
- [Toward Efficient Deep Blind RAW Image Restoration](https://mlsanity.com/paper/2409.18204/) (2024)
- [HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains](https://mlsanity.com/paper/2304.04773/) (2023)
- [Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey](https://mlsanity.com/paper/2404.16223/) (2024)
- [All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines](https://mlsanity.com/paper/2112.09219/) (2021)
- [ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution](https://mlsanity.com/paper/2307.12751/) (2023)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)
- [ISP-Agnostic Image Reconstruction for Under-Display Cameras](https://mlsanity.com/paper/2111.01511/) (2021)

## Abstract (arXiv)

Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic training data by simulating the imaging process of digital cameras. And to remedy the information loss of the input, we develop a dual convolutional neural network to exploit the originally captured radiance information in raw images. In addition, we propose to learn a spatially-variant color transformation which helps more effective color corrections. Extensive experiments demonstrate that super-resolution with raw data helps recover fine details and clear structures, and more importantly, the proposed network and data generation pipeline achieve superior results for single image super-resolution in real scenarios.