mlsanityData to 7 Oct 2026

DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning

arXiv 2207.03081 ↗First posted 7 Jul 2022cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a multi-objective camera ISP framework that utilizes Deep Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and conventional ISP tools. The proposed DRL-based camera ISP framework iteratively selects a proper tool from the toolbox and applies it to the image to maximize a given vision task-specific reward function. For this purpose, we implement total 51 ISP tools that include exposure correction, color-and-tone correction, white balance, sharpening, denoising, and the others. We also propose an efficient DRL network architecture that can extract the various aspects of an image and make a rigid mapping relationship between images and a large number of actions. Our proposed DRL-based ISP framework effectively improves the image quality according to each vision task such as RAW-to-RGB image restoration, 2D object detection, and monocular depth estimation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

29 of 47 references.

References · 29

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Mask R-CNNcited by 7,259
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2015Prioritized Experience Replaycited by 1,070
  7. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  8. 2018Learning to See in the Darkcited by 459
  9. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  10. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  11. 2019Soft Actor-Critic for Discrete Action Settingscited by 161
  12. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
17 more
  1. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  2. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  3. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  4. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  5. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  6. 2020Deep White-Balance Editingcited by 54
  7. 2018Crafting a Toolchain for Image Restoration by Deep Reinforcement Learningcited by 45
  8. 2019CameraNet: A Two-Stage Framework for Effective Camera ISP Learningcited by 38
  9. 2020AWNet: Attentive Wavelet Network for Image ISPcited by 38
  10. 2017Reconfiguring the Imaging Pipeline for Computer Visioncited by 32
  11. 2017Exposure: A White-Box Photo Post-Processing Frameworkcited by 27
  12. 2019Automatic ISP image quality tuning using non-linear optimizationcited by 20
  13. 2020An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Searchcited by 12
  14. 2019Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessmentcited by 10
  15. 2020Learning a Reinforced Agent for Flexible Exposure Bracketing Selectioncited by 6
  16. 2020Learning Multi-Scale Photo Exposure Correctioncited by 3
  17. 2016Learning Adaptive Parameter Tuning for Image Processingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 2.

4 papers.