Update README.md
Browse files
README.md
CHANGED
|
@@ -114,10 +114,6 @@ The model was trained on [Pre-Training Dataset](https://huggingface.co/datasets/
|
|
| 114 |
|
| 115 |
#### Preprocessing
|
| 116 |
|
| 117 |
-
Here's a more concise version of your original paragraph, maintaining the essential information:
|
| 118 |
-
|
| 119 |
-
---
|
| 120 |
-
|
| 121 |
**Preprocessing of Large-Scale Image Data for Photorealism Enhancement**
|
| 122 |
This section details our methodology for preprocessing a large-scale dataset of approximately **117 million game-rendered frames** from **9 AAA video games** and **1.24 billion real-world images** from Mapillary Vistas and Cityscapes, all in 4K resolution. The goal is to pair game frames with real images that exhibit the highest cosine similarity based on structural and visual features, ensuring alignment of fine details like object positions, level of detail and motion blur.
|
| 123 |
|
|
|
|
| 114 |
|
| 115 |
#### Preprocessing
|
| 116 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
**Preprocessing of Large-Scale Image Data for Photorealism Enhancement**
|
| 118 |
This section details our methodology for preprocessing a large-scale dataset of approximately **117 million game-rendered frames** from **9 AAA video games** and **1.24 billion real-world images** from Mapillary Vistas and Cityscapes, all in 4K resolution. The goal is to pair game frames with real images that exhibit the highest cosine similarity based on structural and visual features, ensuring alignment of fine details like object positions, level of detail and motion blur.
|
| 119 |
|