sarafridov
commented
1 year ago Apologies for the slow response...this is difficult to debug since I'm not sure what is different between the two datasets that would make things break on one of them although it works on the other. I don't think there would be any issue with changing the number of views. Was the preprocessing (including computing ist weights) done the same on both datasets? It's also likely to work fine as a fallback option if you run without ist sampling for the dataset where that errors, though details in the dynamic regions will be slightly blurrier.
Dear authors, I'm really appreciated for your excellent work and neat code. I'm currently running k-planes with my multiview dataset after converting to a format that is compatible with DyNeRF. I've tried two personal datasets with the default "dynerf_hybrid.py" configurations. In the case of Dataset 1(consisting of nine views with a resolution of 1920x1088 per view), it works fine until 90001 iterations However, in the case of Dataset 2(consisting of sixteen views with a resolution 1920x1088 per view), it throws out the following error at the iterations equal to "ist_step".
File "D:\ETRI\2023\Immersive\Standardization\INVR\K-Planes-main\plenoxels\datasets\video_datasets.py", line 268, in getitem "timestamps": self.timestamps[index], # (num_rays or 1, ) IndexError: index 858331320 is out of bounds for dimension 0 with size 501350400
Am I running something wrong? Thank you very much.