Pretrained Weights Questions

[asuka-su]

Hi, authors! Thank you for open-sourcing your codes! Really amazing work!

I'm wondering if you plan to release the pretrained weights and test code on SPIn-NeRF datasets or other datasets mentioned in the paper? Currently I'm interested in reproducing the quantitative results.

Thank you for your help!

[Jumpat]

Hi, sorry for the late response. However, since SAGA is a per-scene optimization method and only requires one or two hours of training per scene, we did not keep the original checkpoints on our lab server (due to limited SSD storage).