Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,14 @@ license: apache-2.0
|
|
| 4 |
---
|
| 5 |
# VideoReward
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
## Introduction
|
| 8 |
Welcome to VideoReward, a VLM-based reward model introduced in our paper [Improving Video Generation with Human Feedback](https://arxiv.org/abs/2501.13918). VideoReward is a multi-dimensional reward model that evaluates generated videos on three critical aspects:
|
| 9 |
* Visual Quality (VQ): The clarity, aesthetics, and single-frame reasonableness.
|
|
|
|
| 4 |
---
|
| 5 |
# VideoReward
|
| 6 |
|
| 7 |
+
<p align="center"> <strong> Improving Video Generation with Human Feedback </strong> </p>
|
| 8 |
+
|
| 9 |
+
<div align="center">
|
| 10 |
+
<p align="center">
|
| 11 |
+
📃 <a href="https://arxiv.org/abs/2501.13918" target="_blank">[Paper]</a> • 🌐 <a href="https://gongyeliu.github.io/videoalign/" target="_blank">[Project Page]</a> • 🤗<a href="#" target="_blank">[VideoGen-RewardBench]</a>
|
| 12 |
+
</p>
|
| 13 |
+
</div>
|
| 14 |
+
|
| 15 |
## Introduction
|
| 16 |
Welcome to VideoReward, a VLM-based reward model introduced in our paper [Improving Video Generation with Human Feedback](https://arxiv.org/abs/2501.13918). VideoReward is a multi-dimensional reward model that evaluates generated videos on three critical aspects:
|
| 17 |
* Visual Quality (VQ): The clarity, aesthetics, and single-frame reasonableness.
|