Could you please make the training dataset publicly available?
In the original paper, you mentioned: “Training ZipNeRF on ScanNet++ data required approximately 280 × 2.5 × 8 GPU hours. We will release our processed data to benefit the research community.”
I would also like to ask: How did you obtain the upsampled depth maps for the ARKitScenes dataset?
Could you please make the training dataset publicly available?
In the original paper, you mentioned: “Training ZipNeRF on ScanNet++ data required approximately 280 × 2.5 × 8 GPU hours. We will release our processed data to benefit the research community.”
I would also like to ask: How did you obtain the upsampled depth maps for the ARKitScenes dataset?