This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy. First, to take into account the PC sparsity, our method adaptively partitions a point cloud into multiple voxel block sizes. This partitioning is signalled via an octree. Second, we employ a deep auto-regressive generative model to estimate the occupancy probability of each voxel given the previously encoded ones. We then employ the estimated probabilities to code efficiently a block using a context-based arithmetic coder. Our context has variable size and can expand beyond the current block to learn more accurate probabilities. We also consider using data augmentation techniques to increase the generalization capability of the learned probability models, in particular in the presence of noise and lower-density point clouds. Experimental evaluation, performed on a variety of point clouds from four different datasets and with diverse characteristics, demonstrates that our method reduces significantly (by up to 30%) the rate for lossless coding compared to the state-of-the-art MPEG codec.
翻译:本文建议使用无损点云(PC) 几何压缩方法, 使用神经网络来估计 voxel 占用的概率分布。 首先, 考虑到 PC 的广度, 我们的方法将点云适应性地分割成多个 voxel 区块大小。 此分区是通过八纹树表示的。 第二, 我们使用一个深度的自动递增基因模型来估计每个 voxel 的占用概率。 然后, 我们使用估计的概率来使用基于背景的算术解器来有效地对块进行编码。 我们的上下文大小不一, 可以扩展到当前区块以外, 以了解更准确的概率。 我们还考虑使用数据增强技术来提高所学的概率模型的通用能力, 特别是在有噪音和低密度点云的情况下。 实验性评估从四个不同的数据集和不同特性的不同点云层中进行, 表明我们的方法大大降低了( 高达 30 % ) 与状态的 MPEG 代码相比, 无损计算率的比例。