Update README.md

README.md

@@ -25,7 +25,7 @@ arXiv 2023
 
 ### Pre-trained weights
 
-* **[gmflow_sintel-0c07dcb3.pth](https://huggingface.co/donydchen/matchnerf/resolve/main/gmflow_sintel-0c07dcb3.pth)**: Pre-trained weights for [GMFlow](https://github.com/haofeixu/gmflow), used to initialize our backbone when training.
+* **[gmflow_sintel-0c07dcb3.pth](https://huggingface.co/donydchen/matchnerf/resolve/main/gmflow_sintel-0c07dcb3.pth)**: Pre-trained weights for [GMFlow](https://github.com/haofeixu/gmflow), used to initialize our backbone when training, provided as a backup of the original available on [Google Drive](https://drive.google.com/file/d/1d5C5cgHIxWGsFR1vYs5XrQbbUiZl9TX2/view).
 * **[matchnerf_3v.pth](https://huggingface.co/donydchen/matchnerf/resolve/main/matchnerf_3v.pth)**: Pre-trained weights for [MatchNeRF](https://github.com/donydchen/matchnerf) using DTU dataset, trained using 3 input views. Used for benchmarks testing.
 * **[matchnerf_3v_ibr.pth](https://huggingface.co/donydchen/matchnerf/resolve/main/matchnerf_3v_ibr.pth)**: Pre-trained weights for [MatchNeRF](https://github.com/donydchen/matchnerf) using IBRNet datasets, trained using 3 input views. More suitable for in-the-wild scenes.