# Iterative Prompt Learning for Unsupervised Backlit Image Enhancement

arXiv: https://arxiv.org/abs/2303.17569 · HTML: https://mlsanity.com/paper/2303.17569/

## Key facts

- Cited by 107 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Open-Vocabulary DETR with Conditional Matching](https://mlsanity.com/paper/2203.11876/) (2022)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [LEDNet: Joint Low-light Enhancement and Deblurring in the Dark](https://mlsanity.com/paper/2202.03373/) (2022)
- [Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11831/) (2023)

## Built on by (most cited first, 30 of 107)

- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model](https://mlsanity.com/paper/2403.11157/) (2024)
- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration](https://mlsanity.com/paper/2408.15994/) (2024)
- [Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement](https://mlsanity.com/paper/2405.03349/) (2024)
- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment](https://mlsanity.com/paper/2403.10854/) (2024)
- [Language-driven All-in-one Adverse Weather Removal](https://mlsanity.com/paper/2312.01381/) (2023)
- [Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving](https://mlsanity.com/paper/2404.04804/) (2024)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model](https://mlsanity.com/paper/2410.23905/) (2024)
- [SPIRE: Semantic Prompt-Driven Image Restoration](https://mlsanity.com/paper/2312.11595/) (2023)
- [NightHaze: Nighttime Image Dehazing via Self-Prior Learning](https://mlsanity.com/paper/2403.07408/) (2024)
- [UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration](https://mlsanity.com/paper/2505.06683/) (2025)
- [Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion](https://mlsanity.com/paper/2401.03788/) (2024)
- [LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration](https://mlsanity.com/paper/2410.15385/) (2024)
- [Progressive Pretext Task Learning for Human Trajectory Prediction](https://mlsanity.com/paper/2407.11588/) (2024)
- [AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement](https://mlsanity.com/paper/2407.14900/) (2024)
- [Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision](https://mlsanity.com/paper/2504.04903/) (2025)
- [All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Model](https://mlsanity.com/paper/2411.07445/) (2024)
- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)
- [RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement](https://mlsanity.com/paper/2404.01889/) (2024)
- [Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models](https://mlsanity.com/paper/2409.02101/) (2024)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos](https://mlsanity.com/paper/2401.03522/) (2024)
- [DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement](https://mlsanity.com/paper/2308.09279/) (2023)
- [UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt](https://mlsanity.com/paper/2407.13108/) (2024)
- [When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2507.09524/) (2025)
- [Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance](https://mlsanity.com/paper/2312.15855/) (2023)
- [A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis](https://mlsanity.com/paper/2402.12760/) (2024)

## Abstract (arXiv)

We propose a novel unsupervised backlit image enhancement method, abbreviated as CLIP-LIT, by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel-level image enhancement. We show that the open-world CLIP prior not only aids in distinguishing between backlit and well-lit images, but also in perceiving heterogeneous regions with different luminance, facilitating the optimization of the enhancement network. Unlike high-level and image manipulation tasks, directly applying CLIP to enhancement tasks is non-trivial, owing to the difficulty in finding accurate prompts. To solve this issue, we devise a prompt learning framework that first learns an initial prompt pair by constraining the text-image similarity between the prompt (negative/positive sample) and the corresponding image (backlit image/well-lit image) in the CLIP latent space. Then, we train the enhancement network based on the text-image similarity between the enhanced result and the initial prompt pair. To further improve the accuracy of the initial prompt pair, we iteratively fine-tune the prompt learning framework to reduce the distribution gaps between the backlit images, enhanced results, and well-lit images via rank learning, boosting the enhancement performance. Our method alternates between updating the prompt learning framework and enhancement network until visually pleasing results are achieved. Extensive experiments demonstrate that our method outperforms state-of-the-art methods in terms of visual quality and generalization ability, without requiring any paired data.