Add model card
Browse filesThis PR adds a model card for MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement, including links to the paper and code repository. It also sets the pipeline tag to `image-to-image` so the model is discoverable in the Hub.
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-to-image
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement
|
| 6 |
+
|
| 7 |
+
This repository contains the pretrained model presented in [MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement](https://huggingface.co/papers/2610.24680).
|
| 8 |
+
|
| 9 |
+
MESS is a diffusion-based framework that synthesizes multi-exposure sequences from a single RGB image, enabling generalizable low-light enhancement, exposure correction, and backlit image enhancement.
|
| 10 |
+
|
| 11 |
+
Code and usage instructions: [https://github.com/PolyU-VCLab/MESS](https://github.com/PolyU-VCLab/MESS)
|