Add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- video-deblurring
|
| 5 |
+
- diffusion
|
| 6 |
+
- replica
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# VD-Diff trained on Replica
|
| 10 |
+
|
| 11 |
+
Checkpoints from [VD-Diff](https://github.com/Chen-Rao/VD-Diff) (Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model, ECCV 2024) trained on the Replica scenes.
|
| 12 |
+
|
| 13 |
+
Code that produced these checkpoints: <https://github.com/1zsw123/pretraineddatasetcode>
|
| 14 |
+
|
| 15 |
+
## Files
|
| 16 |
+
|
| 17 |
+
| File | Stage | Step | Size |
|
| 18 |
+
|---|---|---|---|
|
| 19 |
+
| `S1/net_g_200000.pth` | Stage 1 (KPN pre-train) | 200k | 38 MB |
|
| 20 |
+
| `S3/net_g_175000.pth` | Stage 3 (diffusion fine-tune) | 175k | 48 MB |
|
| 21 |
+
|
| 22 |
+
## How to use
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
from huggingface_hub import hf_hub_download
|
| 26 |
+
s1 = hf_hub_download("zhaoshiwen/VD-Diff-Replica", "S1/net_g_200000.pth")
|
| 27 |
+
s3 = hf_hub_download("zhaoshiwen/VD-Diff-Replica", "S3/net_g_175000.pth")
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
Then point `pretrain_network_S1` / `pretrain_network_S2` in the VD-Diff training YAML at these paths. See the upstream README for the training pipeline.
|