Implement some state-of-the-art methods of Semantic Scene Completion (SSC) task in PyTorch. [1] 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior (CVPR 2020)
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 ?
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