Hi, thank you for the good work! I would like to use your pretrained model to get latent codes using point clouds or .off files. I am not able to figure out how to do it. The paper and .yaml files mention that the point cloud is sample at 2048. But seems like in generation.py c = self.model.encode_inputs(inputs) always has inputs of shape 1,300,3
Hi, thank you for the good work! I would like to use your pretrained model to get latent codes using point clouds or .off files. I am not able to figure out how to do it. The paper and .yaml files mention that the point cloud is sample at 2048. But seems like in generation.py
c = self.model.encode_inputs(inputs)
always has inputs of shape 1,300,3