add comparison video
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ VidTok is a family of versatile video tokenizers that delivers state-of-the-art
|
|
| 22 |
|
| 23 |
We train VidTok on a large-scale video dataset and evaluation reveal that VidTok outperforms previous models in both discrete and continuous tokenization, achieving superior results across all evaluated metrics, including PSNR, SSIM, LPIPS, and FVD.
|
| 24 |
|
|
|
|
|
|
|
| 25 |
Resources and technical documentation:
|
| 26 |
|
| 27 |
+ [GitHub](https://github.com/microsoft/VidTok)
|
|
|
|
| 22 |
|
| 23 |
We train VidTok on a large-scale video dataset and evaluation reveal that VidTok outperforms previous models in both discrete and continuous tokenization, achieving superior results across all evaluated metrics, including PSNR, SSIM, LPIPS, and FVD.
|
| 24 |
|
| 25 |
+
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/619b7b1cab4c7b7f16a7d59e/4v2I2YAZJeWSnd7iqntGX.mp4"></video>
|
| 26 |
+
|
| 27 |
Resources and technical documentation:
|
| 28 |
|
| 29 |
+ [GitHub](https://github.com/microsoft/VidTok)
|