Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,19 @@ datasets:
|
|
| 8 |
pipeline_tag: image-to-image
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# Image colorization
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
pipeline_tag: image-to-image
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# Image colorization
|
| 12 |
+
Created a UNet architecture, utilizing transfer learning by using a pretrained ResNet-34 as an encoder.
|
| 13 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/To7FVLusBz1kl8g9HhPIf.png" width="800px"/>
|
| 14 |
+
|
| 15 |
+
The model takes a 224x224 L channel tensor as input and outputs 224x224 ab channels. There are no dedicated datasets for image colorisation, hence I curated my own dataset and used it to train the model. The dataset can be found [here](https://huggingface.co/datasets/ayushshah/coco-2017-image-colorization-224). This repository contains the model weights.
|
| 16 |
+
|
| 17 |
+
<div style="display: flex; justify-content: space-evenly;">
|
| 18 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/5eKOaiTUK4uDeq07MdJIY.png" width="650px"/>
|
| 19 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/MI08kcYgav2ouXlHvvNtu.png" width="650px"/>
|
| 20 |
+
</div>
|
| 21 |
+
|
| 22 |
+
# Refereences
|
| 23 |
+
- [Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification](https://iizuka.cs.tsukuba.ac.jp/projects/colorization/data/colorization_sig2016.pdf)
|
| 24 |
+
- [Colorful Image Colorization](https://arxiv.org/pdf/1603.08511)
|
| 25 |
+
- [Color and Attention for U: Modified Multi Attention U-Net for a Better Image Colorization](https://joiv.org/index.php/joiv/article/view/1828)
|
| 26 |
+
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://arxiv.org/pdf/1704.03915)
|