TorchSSC
TorchSSC copied to clipboard
Using Scannet dataset
Hello, I would like to train and evaluate this implementation on ScanNet dataset. I have the depth frames as 16 bit grayscale images, but I saw that the input format is a little different, as the data is already preprocessed in the provided links. Could you possibly walk me through the process of converting the point clouds to TSDF's and acquiring the 3d depth mappings used in the implementation ?
Kind regards, Kerem Yildirir