Update README.md

README.md

@@ -17,4 +17,4 @@ Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real un
 - more efficient (10x faster) and more lightweight than SD-based models
 - impressive fine-tuned performance with our pre-trained models
 
-For more details, please refer to our [project page](https://depth-anything-v2.github.io/), [github](https://github.com/DepthAnything/Depth-Anything-V2) and [paper]()
+For more details, please refer to our [project page](https://depth-anything-v2.github.io/), [github](https://github.com/DepthAnything/Depth-Anything-V2) and [paper](https://arxiv.org/abs/2406.09414).