Open machengcheng2016 opened 1 year ago
Hi, thanks for your interest!
weighted_loss
should not be used for the current paper results (#30 was posted during our v1 arxiv). Could you please clarify what problems you encounter when re-producing the results using the current configs? Meanwhile, I'll also upload the args and configs to the pre-trained log folders for reference.
Greetings! I find the config files that you release now are actually neglecting many important training options, for example, whether use
weighted_loss
or not (refer to this issue #30). Besides, the pretrained logs you provided in download_models.sh are actually missing the args.txt and config.txt. Since these hyper-parameters are vital to reproduce the reported performances in paper, could you please completely upload these files for each scene and each dataset? Or it is really hard for for future works to make experimental comparisons with DSNeRF. Thanks!