T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning

arXiv:2312.10217v2 Announce Type: replace
Abstract: The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal information, which is inherent in the LiDAR point cloud sequence, is consistently disregarded. To better utilize this property, we propose an effective pre-training strategy, namely Temporal Masked Auto-Encoders (T-MAE), which takes as input temporally adjacent frames and learns temporal dependency. A SiamWCA backbone, containing a Siamese encoder and a …

abstract annotated data arxiv autoencoders cloud cs.cv data information lidar pre-training property representation representation learning scholars temporal training type understanding