# CARDIE: clustering algorithm on relevant descriptors for image enhancement

arXiv: https://arxiv.org/abs/2509.06116 · HTML: https://mlsanity.com/paper/2509.06116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Unsupervised Learning: Comparative Analysis of Clustering Techniques on High-Dimensional Data](https://mlsanity.com/paper/2503.23215/) (2025)

## Abstract (arXiv)

Automatic image clustering is a cornerstone of computer vision, yet its application to image enhancement remains limited, primarily due to the difficulty of defining clusters that are meaningful for this specific task. To address this issue, we introduce CARDIE, an unsupervised algorithm that clusters images based on their color and luminosity content. In addition, we introduce a method to quantify the impact of image enhancement algorithms on luminance distribution and local variance. Using this method, we demonstrate that CARDIE produces clusters more relevant to image enhancement than those derived from semantic image attributes. Furthermore, we demonstrate that CARDIE clusters can be leveraged to resample image enhancement datasets, leading to improved performance for tone mapping and denoising algorithms. To encourage adoption and ensure reproducibility, we publicly release CARDIE code on our GitHub.