3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

arXiv:2304.06911v2 Announce Type: replace
Abstract: Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is …

abstract arxiv autoencoder autoencoders cloud colors computer computer vision cs.cv domain feature features image nlp pixels prediction pretraining restore success type vision