# DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping

arXiv: https://arxiv.org/abs/2604.03402 · HTML: https://mlsanity.com/paper/2604.03402/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 52 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [Burst Image Restoration and Enhancement](https://mlsanity.com/paper/2110.03680/) (2021)
- [Mobile Computational Photography: A Tour](https://mlsanity.com/paper/2102.09000/) (2021)
- [RENOIR - A Dataset for Real Low-Light Image Noise Reduction](https://mlsanity.com/paper/1409.8230/) (2014)
- [Burstormer: Burst Image Restoration and Enhancement Transformer](https://mlsanity.com/paper/2304.01194/) (2023)
- [Deep Tone Mapping Operator for High Dynamic Range Images](https://mlsanity.com/paper/1908.04197/) (2019)
- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [Towards Real-World Burst Image Super-Resolution: Benchmark and Method](https://mlsanity.com/paper/2309.04803/) (2023)
- [Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping](https://mlsanity.com/paper/2310.17190/) (2023)
- [A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions](https://mlsanity.com/paper/2302.04032/) (2023)
- [NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution](https://mlsanity.com/paper/2506.02197/) (2025)
- [Edge-Aware Deep Image Deblurring](https://mlsanity.com/paper/1907.02282/) (2019)
- [Learning a self-supervised tone mapping operator via feature contrast masking loss](https://mlsanity.com/paper/2110.09866/) (2021)
- [Convolutional Neural Networks Considering Local and Global features for Image Enhancement](https://mlsanity.com/paper/1905.02899/) (2019)
- [High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network](https://mlsanity.com/paper/2510.11613/) (2025)
- [Which tone-mapping operator is the best? A comparative study of perceptual quality](https://mlsanity.com/paper/1601.04450/) (2016)
- [Learning Differential Pyramid Representation for Tone Mapping](https://mlsanity.com/paper/2412.01463/) (2024)
- [MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling](https://mlsanity.com/paper/2502.20824/) (2025)

## Abstract (arXiv)

Smartphone cameras have gained immense popularity with the adoption of high-resolution and high-dynamic range imaging. As a result, high-performance camera Image Signal Processors (ISPs) are crucial in generating high-quality images for the end user while keeping computational costs low. In this paper, we propose DRIFT (Deep Restoration, ISP Fusion, and Tone-mapping): an efficient AI mobile camera pipeline that generates high quality RGB images from hand-held raw captures. The first stage of DRIFT is a Multi-Frame Processing (MFP) network that is trained using a adversarial perceptual loss to perform multi-frame alignment, denoising, demosaicing, and super-resolution. Then, the output of DRIFT-MFP is processed by a novel deep-learning based tone-mapping (DRIFT-TM) solution that allows for tone tunability, ensures tone-consistency with a reference pipeline, and can be run efficiently for high-resolution images on a mobile device. We show qualitative and quantitative comparisons against state-of-the-art MFP and tone-mapping methods to demonstrate the effectiveness of our approach.