Update README.md

README.md

@@ -1,3 +1,39 @@
----
-license: mit
----
+---
+license: mit
+---
+
+# ✨ ModalFormer: Multimodal Transformer for Low-Light Image Enhancement
+
+<div align="center">
+  
+**[Alexandru Brateanu](https://scholar.google.com/citations?user=ru0meGgAAAAJ&hl=en), [Raul Balmez](https://scholar.google.com/citations?user=vPC7raQAAAAJ&hl=en), [Ciprian Orhei](https://scholar.google.com/citations?user=DZHdq3wAAAAJ&hl=en), [Codruta Ancuti](https://scholar.google.com/citations?user=5PA43eEAAAAJ&hl=en), [Cosmin Ancuti](https://scholar.google.com/citations?user=zVTgt8IAAAAJ&hl=en)**
+
+[![arXiv](https://img.shields.io/badge/arxiv-paper-179bd3)](https://arxiv.org/abs/2401.15204)
+</div>
+
+### Abstract
+*Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on pixel-level transformations of RGB images, neglecting the rich contextual information available from multiple visual modalities. In this paper, we present ModalFormer, the first large-scale multimodal framework for LLIE that fully exploits nine auxiliary modalities to achieve state-of-the-art performance. Our model comprises two main components: a Cross-modal Transformer (CM-T) designed to restore corrupted images while seamlessly integrating multimodal information, and multiple auxiliary subnetworks dedicated to multimodal feature reconstruction. Central to the CM-T is our novel Cross-modal Multi-headed Self-Attention mechanism (CM-MSA), which effectively fuses RGB data with modality-specific features—including deep feature embeddings, segmentation information, geometric cues, and color information—to generate information-rich hybrid attention maps. Extensive experiments on multiple benchmark datasets demonstrate ModalFormer’s state-of-the-art performance in LLIE. Pre-trained models and results are made available at https://github.com/albrateanu/ModalFormer*
+
+## 🆕 Updates
+- `29.07.2025` 🎉 The [**ModalFormer**](https://arxiv.org/abs/2401.15204) paper is now available! Check it out and explore our results and methodology.
+- `28.07.2025` 📦 Pre-trained models and test data published! ArXiv paper version and HuggingFace demo coming soon, stay tuned!
+
+## ⚙️ Setup and Testing
+Please check out the [**GitHub repository**](https://github.com/albrateanu/ModalFormer) for implementation details.
+
+## 📚 Citation
+
+```
+@misc{brateanu2025modalformer,
+      title={ModalFormer: Multimodal Transformer for Low-Light Image Enhancement}, 
+      author={Alexandru Brateanu and Raul Balmez and Ciprian Orhei and Codruta Ancuti and Cosmin Ancuti},
+      year={2025},
+      eprint={2507.20388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2507.20388}, 
+}
+```
+
+## 🙏 Acknowledgements
+We use [this codebase](https://github.com/caiyuanhao1998/Retinexformer) as foundation for our implementation.