Closed pansanity666 closed 11 months ago
Hi, the finetuning only uses the reference views (the test views are kept held out). Yes, you could try lowering the learning rate during fine-tuning and see if that leads to better results.
Hi, the finetuning only uses the reference views (the test views are kept held out). Yes, you could try lowering the learning rate during fine-tuning and see if that leads to better results.
Thanks.
Hi,
I have several confusions about the finetuning for the Generalizable NeRF task (IBRNet, MVSNeRF, etc):
Should I lower down the LR during finetuning?
Best,