Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes-猫眼课题宝

DOI：

10.1109/iccv51070.2023.01344

发表时间：

2023-10

期刊：

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

F. Babiloni;Matteo Maggioni;T. Tanay;Jiankang Deng;A. Leonardis;S. Zafeiriou

深度学习模型在结构化数据上的成功引起了人们对将其应用扩展到非欧几里德域的极大兴趣。在这项工作中，我们引入了一种新的内在算子，适用于表示学习的3D网格。我们的算子是专门定制的，以适应其行为的不规则结构的基础图，并有效地利用其长期的依赖关系，同时确保计算效率和易于优化。特别是，螺旋卷积的框架，提取和变换的顶点在3D网格中的局部螺旋排序的启发，我们提出了一个通用的操作，动态调整螺旋轨迹的长度和参数的转换为每个处理的顶点和网格。然后，我们使用polyadic分解将其稠密权重张量分解为一系列较轻的线性层，分别处理特征和顶点信息，从而显着降低计算复杂度，而不会引入任何严格的归纳偏差。值得注意的是，我们利用动态门控来实现空间自适应性，并诱导全局推理与恒定的时间复杂度受益于一个有效的动态池机制的基础上求和面积表。作为现有架构的形状对应的替代品，我们的操作员显着提高了性能效率的权衡，并在3D形状生成与变形模型实现了最先进的性能，所需的参数数量减少了三倍。项目页面：https://github.com/Fb2221/DFC

The success of deep learning models on structured data has generated significant interest in extending their application to non-Euclidean domains. In this work, we introduce a novel intrinsic operator suitable for representation learning on 3D meshes. Our operator is specifically tailored to adapt its behavior to the irregular structure of the underlying graph and effectively utilize its long-range dependencies, while at the same time ensuring computational efficiency and ease of optimization. In particular, inspired by the framework of Spiral Convolution, which extracts and transforms the vertices in the 3D mesh following a local spiral ordering, we propose a general operator that dynamically adjusts the length of the spiral trajectory and the parameters of the transformation for each processed vertex and mesh. Then, we use polyadic decomposition to factorize its dense weight tensor into a sequence of lighter linear layers that separately process features and vertices information, hence significantly reducing the computational complexity without introducing any stringent inductive biases. Notably, we leverage dynamic gating to achieve spatial adaptivity and induce global reasoning with constant time complexity benefitting from an efficient dynamic pooling mechanism based on Summed-Area-tables. Used as a drop-in replacement on existing architectures for shape correspondence our operator significantly improves the performance-efficiency trade-off, and in 3D shape generation with morphable models achieves state-of-the-art performance with a three-fold reduction in the number of parameters required. Project page: https://github.com/Fb2221/DFC

Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes

文献摘要

相似文献