Over-the-Air Learning-based Geometry Point Cloud Transmission

This paper presents novel solutions for the efficient and reliable transmission of 3D point clouds over wireless channels. We first propose SEPT for the transmission of small-scale point clouds, which encodes the point cloud via an iterative downsampling and feature extraction process. At the receiver, SEPT decoder reconstructs the point cloud with latent reconstruction and offset-based upsampling. A novel channel-adaptive module is proposed to allow SEPT to operate effectively over a wide range of channel conditions. Next, we propose OTA-NeRF, a scheme inspired by neural radiance fields. OTA-NeRF performs voxelization to the point cloud input and learns to encode the voxelized point cloud into a neural network. Instead of transmitting the extracted feature vectors as in the SEPT scheme, it transmits the learned neural network weights over the air in an analog fashion along with few hyperparameters that are transmitted digitally. At the receiver, the OTA-NeRF decoder reconstructs the original point cloud using the received noisy neural network weights. To further increase the bandwidth efficiency of the OTA-NeRF scheme, a fine-tuning algorithm is developed, where only a fraction of the neural network weights are retrained and transmitted. Extensive numerical experiments confirm that both the SEPT and the OTA-NeRF schemes achieve superior or comparable performance over the conventional approaches, where an octree-based or a learning-based point cloud compression scheme is concatenated with a channel code. As an additional advantage, both schemes mitigate the cliff and leveling effects making them particularly attractive for highly mobile scenarios, where accurate channel estimation is challenging if not impossible.