Dataset for content

[loveaca-sunlight]

Thanks for the work you share！
I want to know how to generate the content image, that is, the image inside all_contents folder that is needed in finetune_decoder.
Is it using the original NeRF to directly generate multi-view images?
Are there any additional formatting requirements?
Can you provide a download of this data?

[yihua7]

Hi~ : )
If you are following the readme guidelines to the step of 'Pre-trained Model Preparation', you can directly use the folder of your training images of NeRF (e.g LLFF dataset's content image folders) as all_contents. There is no additional formatting requirements. Just make sure that 'all_contents' is a folder of pure images.