3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining. (arXiv:2304.06911v1 [cs.CV])

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 inessential and restoring intrinsic point …

arxiv autoencoder cloud colors computer computer vision feature features geometry image location nlp pixels prediction recovery restore studies success vision