加速3D非刚性形状匹配，提升效率并统一评测标准
DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited
- 用向量化方法一次性求解所有线性系统，提速最高达33倍
- 发现DiffusionNet空间梯度特征的两种实现差异及其影响
- 提供标准化代码库，支持训练、评估与数据处理
深度函数映射通过学习特征提取器和谱对应求解器，是非刚性3D形状匹配的核心。我们分析开源实现后发现，标准功能映射实现以串行方式求解k个独立线性系统，高谱分辨率下成为计算瓶颈。为此，我们提出一种向量化重构，单次核调用即可求解全部系统，实现最高33倍加速，同时保持精确解。此外，我们识别并记录了主流模型DiffusionNet中空间梯度特征的未被注意的实现差异：两种变体对应不同的切平面变换族，并在多个基准上分析其行为差异。我们还重新审视了部分到部分匹配中的重叠预测评估，表明在不同重叠比例下，平衡准确率是有效的补充指标。为推动社区发展，我们发布开源代码库DeepShapeMatchingKit，集成上述改进，并标准化常见深度形状匹配方法的训练、评估与数据流程。代码地址：https://github.com/xieyizheng/DeepShapeMatchingKit
原文摘要 · Abstract (English)
Deep functional maps, leveraging learned feature extractors and spectral correspondence solvers, are fundamental to non-rigid 3D shape matching. Based on an analysis of open-source implementations, we find that standard functional map implementations solve k independent linear systems serially, which is a computational bottleneck at higher spectral resolution. We thus propose a vectorized reformulation that solves all systems in a single kernel call, achieving up to a 33x speedup while preserving the exact solution. Furthermore, we identify and document a previously unnoticed implementation divergence in the spatial gradient features of the mainstay DiffusionNet: two variants that parameterize distinct families of tangent-plane transformations, and present experiments analyzing their respective behaviors across diverse benchmarks. We additionally revisit overlap prediction evaluation for partial-to-partial matching and show that balanced accuracy provides a useful complementary metric under varying overlap ratios. To share these advancements with the wider community, we present an open-source codebase, DeepShapeMatchingKit, that incorporates these improvements and standardizes training, evaluation, and data pipelines for common deep shape matching methods. The codebase is available at: https://github.com/xieyizheng/DeepShapeMatchingKit
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。