mlsanityData to 7 Oct 2026

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

arXiv 2604.03402 ↗First posted 3 Apr 2026eess.IV cs.CVcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 3 Apr 2026.

Builds on

29 of 52 references.

References · 29

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  9. 2021Multi-Stage Progressive Image Restorationcited by 813
  10. 2022Simple Baselines for Image Restorationcited by 701
  11. 2019Handheld Multi-Frame Super-Resolutioncited by 85
  12. 2021Deep Burst Super-Resolutioncited by 83
17 more
  1. 2021Burst Image Restoration and Enhancementcited by 64
  2. 2021Mobile Computational Photography: A Tourcited by 62
  3. 2014RENOIR - A Dataset for Real Low-Light Image Noise Reductioncited by 36
  4. 2023Burstormer: Burst Image Restoration and Enhancement Transformercited by 32
  5. 2019Deep Tone Mapping Operator for High Dynamic Range Imagescited by 26
  6. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  7. 2023Towards Real-World Burst Image Super-Resolution: Benchmark and Methodcited by 12
  8. 2023Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mappingcited by 12
  9. 2023A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventionscited by 11
  10. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  11. 2019Edge-Aware Deep Image Deblurringcited by 6
  12. 2021Learning a self-supervised tone mapping operator via feature contrast masking losscited by 6
  13. 2019Convolutional Neural Networks Considering Local and Global features for Image Enhancementcited by 4
  14. 2025High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Networkcited by 4
  15. 2016Which tone-mapping operator is the best? A comparative study of perceptual qualitycited by 3
  16. 2024Learning Differential Pyramid Representation for Tone Mappingcited by 3
  17. 2025MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modelingcited by 1

Built on by

Not cited yet.