mlsanityData to 14 Oct 2026

CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing

arXiv 2505.23102 ↗First posted 29 May 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Low-Light Image Enhancement (LLIE) is crucial for improving both human perception and computer vision tasks. This paper addresses two challenges in zero-reference LLIE: obtaining perceptually 'good' images using the Contrastive Language-Image Pre-Training (CLIP) model and maintaining computational efficiency for high-resolution images. We propose CLIP-Utilized Reinforcement learning-based Visual image Enhancement (CURVE). CURVE employs a simple image processing module which adjusts global image tone based on B'ezier curve and estimates its processing parameters iteratively. The estimator is trained by reinforcement learning with rewards designed using CLIP text embeddings. Experiments on low-light and multi-exposure datasets demonstrate the performance of CURVE in terms of enhancement quality and processing speed compared to conventional methods.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

18 of 21 references.

References · 18

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  4. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  5. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
  6. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  7. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  8. 2018Getting to Know Low-light Images with The Exclusively Dark Datasetcited by 157
  9. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  10. 2017Exposure: A White-Box Photo Post-Processing Frameworkcited by 27
  11. 2021ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancementcited by 26
  12. 2024AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detectioncited by 18
6 more
  1. 2024CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustmentcited by 10
  2. 2024Learning to Control Camera Exposure via Reinforcement Learningcited by 9
  3. 2024ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processingcited by 8
  4. 2024Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancementcited by 6
  5. 2025Discovering an Image-Adaptive Coordinate System for Photography Processingcited by 4
  6. 2024Leveraging Content and Context Cues for Low-Light Image Enhancementcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structurescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning
  2. 2024Low-Light Image Enhancement via Generative Perceptual Priors
  3. 2025LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
  4. 2026Dynamic Interpolation for Training-Time Prediction Reshaping in Low-Light Image Enhancement
  5. 2025Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysis
  6. 2024CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement
  7. 2024Zero-Shot Low Light Image Enhancement with Diffusion Prior
  8. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learning