Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction

TL;DR

This paper introduces an attention-based module to improve octree-based point cloud geometry compression by more accurately predicting occupied child nodes, leading to better coding efficiency.

Contribution

The paper proposes the ACNP module that predicts child node occupancy more effectively, addressing limitations of cross-entropy loss in existing models.

Findings

Enhanced coding efficiency demonstrated in experiments

ACNP outperforms traditional methods in accuracy

Improved entropy coding results in better compression

Abstract

In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted by the context model as the loss. This approach converts the problem of predicting the number (a regression problem) and the position (a classification problem) of occupied child nodes into a 255-dimensional classification problem. As a result, it fails to accurately measure the difference between the one-hot encoding and the predicted probability distribution. We first analyze why the cross-entropy loss function fails to accurately measure the difference between the one-hot encoding and the predicted probability distribution. Then, we propose an attention-based child node number prediction (ACNP) module to enhance the context models. The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding. Experimental results demonstrate that the proposed module enhances the coding efficiency of octree-based context models.