Update README.md
Browse files
README.md
CHANGED
|
@@ -64,10 +64,19 @@ python inference.py \
|
|
| 64 |
--image_width <YOUR_TARGET_WIDTH>
|
| 65 |
```
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
## Citation
|
| 68 |
If you find this work useful, please cite:
|
| 69 |
```bibtex
|
| 70 |
-
@article{
|
| 71 |
title={Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion},
|
| 72 |
author={Shiu, Hau-Shiang and Lin, Chin-Yang and Wang, Zhixiang and Hsiao, Chi-Wei and Yu, Po-Fan and Chen, Yu-Chih and Liu, Yu-Lun},
|
| 73 |
journal={arXiv preprint arXiv:2512.23709},
|
|
|
|
| 64 |
--image_width <YOUR_TARGET_WIDTH>
|
| 65 |
```
|
| 66 |
|
| 67 |
+
## Note
|
| 68 |
+
|
| 69 |
+
The provided checkpoint is a **toy / proof-of-concept model** trained on a limited amount of data. As a result, it does not yet cover the full diversity of real-world videos.
|
| 70 |
+
|
| 71 |
+
This checkpoint is mainly intended to demonstrate the **overall pipeline and low-latency feasibility**, rather than to deliver production-level upscaling quality.
|
| 72 |
+
|
| 73 |
+
Artifacts and inconsistent visual quality are therefore expected at this stage.
|
| 74 |
+
|
| 75 |
+
|
| 76 |
## Citation
|
| 77 |
If you find this work useful, please cite:
|
| 78 |
```bibtex
|
| 79 |
+
@article{shiu2025stream,
|
| 80 |
title={Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion},
|
| 81 |
author={Shiu, Hau-Shiang and Lin, Chin-Yang and Wang, Zhixiang and Hsiao, Chi-Wei and Yu, Po-Fan and Chen, Yu-Chih and Liu, Yu-Lun},
|
| 82 |
journal={arXiv preprint arXiv:2512.23709},
|