In recent years, deep functional maps (DFM) have emerged as a leading learning-based framework for non-rigid shape-matching problems, offering diverse network architectures for this domain. This richness also makes exploring better and novel design beliefs for existing powerful DFM components to promote performance meaningful and engaging. This paper delves into this problem and successfully produces the SEDFMNet, a simple yet highly efficient DFM pipeline. To achieve this, we systematically deconstruct the core modules of the general DFM framework and analyze key design choices in existing approaches to identify the most critical components through extensive experiments. By reassembling these crucial components, we culminate in developing our SEDFMNet, which features a simpler structure than conventional DFM pipelines while delivering superior performance. Our approach is rigorously validated through comprehensive experiments on diverse datasets, where the SEDFMNet consistently achieves state-of-the-art results, even in challenging scenarios such as non-isometric shape matching and shape matching with topological noise. Our work offers fresh insights into DFM research and opens new avenues for advancing this field.

Traditional deep functional map frameworks are widely used for 3D shape matching; however, many methods fail to adaptively capture the relevant frequency information required for functional map estimation in complex scenarios, leading to poor performance, especially under significant deformations. To address these challenges, we propose a novel unsupervised learning-based framework, Deep Frequency Awareness Functional Maps (DFAFM), specifically designed to tackle diverse shape-matching problems. Our approach introduces the Spectral Filter Operator Preservation constraint, which ensures the preservation of critical frequency information. These constraints promote frequency awareness by learning a set of spectral filters and incorporating them as a loss function to jointly supervise the functional maps, pointwise maps, and spectral filters. The spectral filters are constructed using orthonormal Jacobi polynomials with learnable coefficients, enabling adaptive and efficient frequency representation. Furthermore, we propose a refinement strategy that leverages the learned spectral filters and constraints to enhance the accuracy of the final pointwise map. Extensive experiments conducted on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art approaches, particularly in challenging scenarios involving non-isometric deformations and inconsistent topology.

Abstract In deep functional maps, the regularizer computing the functional map is especially crucial for ensuring the global consistency of the computed pointwise map. As the regularizers integrated into deep learning should be differentiable, it is not trivial to incorporate informative axiomatic structural constraints into the deep functional map, such as the orientation‐preserving term. Although commonly used regularizers include the Laplacian‐commutativity term and the resolvent Laplacian commutativity term, these are limited to single‐scale analysis for capturing geometric information. To this end, we propose a novel and theoretically well‐justified regularizer commuting the functional map with the multiscale spectral manifold wavelet operator. This regularizer enhances the isometric constraints of the functional map and is conducive to providing it with better structural properties with multiscale analysis. Furthermore, we design an unsupervised deep functional map with the regularizer in a fully differentiable way. The quantitative and qualitative comparisons with several existing techniques on the (near‐)isometric and non‐isometric datasets show our method's superior accuracy and generalization capabilities. Additionally, we illustrate that our regularizer can be easily inserted into other functional map methods and improve their accuracy.

In traditional deep functional maps for non-rigid shape correspondence, estimating a functional map including high-frequency information requires enough linearly independent features via the least square method, which is prone to be violated in practice, especially at an early stage of training, or costly post-processing, e.g. ZoomOut. In this paper, we propose a novel method called RFMNet (Robust Deep Functional Map Networks), which jointly considers training stability and more geometric shape features than previous works. We directly first produce a pointwise map by resorting to optimal transport and then convert it to an initial functional map. Such a mechanism mitigates the requirements for the descriptor and avoids the training instabilities resulting from the least square solver. Benefitting from the novel strategy, we successfully integrate a state-of-the-art geometric regularization for further optimizing the functional map, which substantially filters the initial functional map. We show our novel computing functional map module brings more stable training even under encoding the functional map with high-frequency information and faster convergence speed. Considering the pointwise and functional maps, an unsupervised loss is presented for penalizing the correspondence distortion of Delta functions between shapes. To catch discretization-resistant and orientation-aware shape features with our network, we utilize DiffusionNet as a feature extractor. Experimental results demonstrate our apparent superiority in correspondence quality and generalization across various shape discretizations and different datasets compared to the state-of-the-art learning methods.

Shape descriptors have recently gained popularity in shape matching, statistical shape modeling, etc. Their discriminative ability and efficiency play a decisive role in these tasks. In this paper, we first propose a novel handcrafted anisotropic spectral descriptor using Chebyshev polynomials, called the anisotropic Chebyshev descriptor (ACD); it can effectively capture shape features in multiple directions. The ACD inherits many good characteristics of spectral descriptors, such as being intrinsic, robust to changes in surface discretization, etc. Furthermore, due to the orthogonality of Chebyshev polynomials, the ACD is compact and can disambiguate intrinsic symmetry since several directions are considered. To improve the ACD’s discrimination ability, we construct a Chebyshev spectral manifold convolutional neural network (CSMCNN) that optimizes the ACD and produces a learned ACD. Our experimental results show that the ACD outperforms existing state-of-the-art handcrafted descriptors. The combination of the ACD and the CSMCNN is better than other state-of-the-art learned descriptors in terms of discrimination, efficiency, and robustness to changes in shape resolution and discretization.

Abstract We propose a novel unsupervised learning approach for computing correspondences between non‐rigid 3D shapes. The core idea is that we integrate a novel structural constraint into the deep functional map pipeline, a recently dominant learning framework for shape correspondence, via a powerful spectral manifold wavelet transform (SMWT). As SMWT is isometrically invariant operator and can analyze features from multiple frequency bands, we use the multiscale SMWT results of the learned features as function preservation constraints to optimize the functional map by assuming each frequency‐band information of the descriptors should be correspondingly preserved by the functional map. Such a strategy allows extracting significantly more deep feature information than existing approaches which only use the learned descriptors to estimate the functional map. And our formula strongly ensure the isometric properties of the underlying map. We also prove that our computation of the functional map amounts to filtering processes only referring to matrix multiplication. Then, we leverage the alignment errors of intrinsic embedding between shapes as a loss function and solve it in an unsupervised way using the Sinkhorn algorithm. Finally, we utilize DiffusionNet as a feature extractor to ensure that discretization‐resistant and directional shape features are produced. Experiments on multiple challenging datasets prove that our method can achieve state‐of‐the‐art correspondence quality. Furthermore, our method yields significant improvements in robustness to shape discretization and generalization across the different datasets. The source code and trained models will be available at https://github.com/HJ-Xu/WTFM-Layer .

The functional map framework has proven to be extremely effective for representing dense correspondences between deformable shapes. A key step in this framework is to formulate suitable preservation constraints to encode the geometric information that must be preserved by the unknown map. For this issue, we construct novel and powerful constraints to determine the functional map, where multiscale spectral manifold wavelets are required to be preserved at each scale correspondingly. Such constraints allow us to extract significantly more information than previous methods, especially those based on descriptor preservation constraints, and strongly ensure the isometric property of the map. In addition, we also propose a remarkable efficient iterative method to alternatively update the functional maps and pointwise maps. Moreover, when we use the tight wavelet frames in iterations, the computation of the functional maps boils down to a simple filtering procedure with low-pass and various band-pass filters, which avoids time-consuming solving large systems of linear equations commonly presented in functional maps. We demonstrate on a wide variety of experiments with different datasets that our approach achieves significant improvements both in the shape correspondence quality and the computing efficiency.

Abstract In this paper, we present a powerful spectral shape descriptor for shape analysis, named Anisotropic Spectral Manifold Wavelet Descriptor (ASMWD). We proposed a novel manifold harmonic signal processing tool termed Anisotropic Spectral Manifold Wavelet Transform (ASMWT) first. ASMWT allows to comprehensively analyse signals from multiple wavelet diffusion directions on local manifold regions of the shape with a series of low‐pass and band‐pass frequency filters in each direction. Based on the ASMWT coefficients of a very simple signal, the ASMWD is efficiently constructed as a localizable and discriminative multi‐scale point descriptor. Since the wavelets used in our descriptor are direction‐sensitive and able to robustly reconstruct the signals with a finite number of scales, it makes our descriptor compact, efficient, and unambiguous under intrinsic symmetry. The extensive experiments demonstrate that our descriptor achieves significantly better performance than the state‐of‐the‐art descriptors and can greatly improve the performance of shape matching methods including both handcrafted and learning‐based methods.

Establishing correspondence between shapes is a very important and active research topic in many domains. Due to the powerful ability of deep learning on geometric data, lots of attractive results have been achieved by convolutional neural networks (CNNs). In this paper, we propose a novel architecture for shape correspondence, termed Anisotropic Chebyshev spectral CNNs (ACSCNNs), based on a new extension of the manifold convolution operator. The extended convolution operators aggregate the local features of signals by a set of oriented kernels around each point, which allows to much more comprehensively capture the intrinsic signal information. Rather than using fixed oriented kernels in the spatial domain in previous CNNs, in our framework, the kernels are learned by spectral filtering, based on the eigen-decompositions of multiple Anisotropic Laplace-Beltrami Operators. To reduce the computational complexity, we employ an explicit expansion of the Chebyshev polynomial basis to represent the spectral filters whose expansion coefficients are trainable. Through the benchmark experiments of shape correspondence, our architecture is demonstrated to be efficient and be able to provide better than the state-of-the-art results in several datasets even if using constant functions as inputs.