arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.08528eess.IVcs.CVcs.MM
收藏

通过基于注意力的子节点数预测增强用于点云几何压缩的基于八叉树的上下文模型

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

Chang Sun, Hui Yuan, Xiaolong Mao, Xin Lu, Raouf Hamzaoui

AI总结:

针对点云几何压缩中八叉树上下文模型交叉熵损失无法准确衡量分布差异的问题,提出基于注意力的子节点数预测模块,通过预测占用子节点数并映射为8维向量辅助概率预测,提升了编码效率。

摘要:

在点云几何压缩中,大多数基于八叉树的上下文模型将节点占用的独热编码与上下文模型预测的概率分布之间的交叉熵作为损失。该方法将预测占用子节点的数量(回归问题)和位置(分类问题)转化为255维分类问题,导致其无法准确衡量独热编码与预测概率分布之间的差异。我们首先分析了交叉熵损失函数无法准确衡量独热编码与预测概率分布之间差异的原因,随后提出了基于注意力的子节点数预测(ACNP)模块以增强上下文模型。该模块能够预测占用子节点的数量,并将其映射为8维向量,辅助上下文模型预测当前节点的占用概率分布,以实现高效熵编码。实验结果表明,该模块提升了基于八叉树的上下文模型的编码效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑