论文标题
Rocnet：递归OCTREE网络，用于有效的3D深度表示
RocNet: Recursive Octree Network for Efficient 3D Deep Representation
论文作者
论文摘要
我们引入了一个深层递归OCTREE网络，用于压缩3D体素数据。我们的网络会在类似自动编码器的网络中压缩任何大小的体素网格，以降低到非常小的潜在空间。我们显示了在潜在空间中压缩32、64和128网格的结果。我们通过三个实验证明了我们提出的方法在几个公开可用数据集上的有效性和效率：3D形状分类，3D形状重建和形状产生。实验结果表明，与现有方法相比，我们的算法保持准确性，同时使用较短的训练时间消耗记忆力，尤其是在3D重建任务中。
We introduce a deep recursive octree network for the compression of 3D voxel data. Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network. We show results for compressing 32, 64 and 128 grids down to just 80 floats in the latent space. We demonstrate the effectiveness and efficiency of our proposed method on several publicly available datasets with three experiments: 3D shape classification, 3D shape reconstruction, and shape generation. Experimental results show that our algorithm maintains accuracy while consuming less memory with shorter training times compared to existing methods, especially in 3D reconstruction tasks.
