Deep Frequency-Aware Functional Maps for Robust Shape Matching
- URL: http://arxiv.org/abs/2402.03904v2
- Date: Tue, 25 Jun 2024 12:13:58 GMT
- Title: Deep Frequency-Aware Functional Maps for Robust Shape Matching
- Authors: Feifan Luo, Qinsong Li, Ling Hu, Haibo Wang, Xinru Liu, Shengjun Liu, Hongyang Chen,
- Abstract summary: We propose a novel unsupervised learning-based framework called Deep Frequency-Aware Functional Maps.
We first introduce a general constraint called Spectral Filter Operator Preservation to compute desirable functional maps.
We then directly utilize the proposed constraint as a loss function to supervise functional maps, pointwise maps, and filter functions simultaneously.
- Score: 17.276162941967943
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep functional map frameworks are widely employed for 3D shape matching. However, most existing deep functional map methods cannot adaptively capture important frequency information for functional map estimation in specific matching scenarios, i.e., lacking \textit{frequency awareness}, resulting in poor performance when dealing with large deformable shape matching. To this end, we propose a novel unsupervised learning-based framework called Deep Frequency-Aware Functional Maps, which can gracefully cope with various shape matching scenarios. We first introduce a general constraint called Spectral Filter Operator Preservation to compute desirable functional maps, where the spectral filter operator encodes informative frequency information and can promote frequency awareness for deep functional map frameworks by learning a set of filter functions. Then, we directly utilize the proposed constraint as a loss function to supervise functional maps, pointwise maps, and filter functions simultaneously, where the filter functions are derived from the orthonormal Jacobi basis, and the coefficients of the basis are learnable parameters. Finally, we develop an effective refinement strategy to improve the final pointwise map, which incorporates our constraint and learned filter functions, leading to more robust and accurate correspondences during the inference process. Extensive experimental results on various datasets demonstrate that our approach outperforms the existing state-of-the-art methods, especially in challenging settings like datasets with non-isometric deformation and inconsistent topology.
Related papers
- A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.
We also develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
Our proposed ReSFU framework consistently achieves satisfactory performance on different segmentation applications.
arXiv Detail & Related papers (2024-07-02T14:12:21Z) - Memory-Scalable and Simplified Functional Map Learning [32.088809326158554]
We introduce a novel memory-scalable and efficient functional map learning pipeline.
By leveraging the structure of functional maps, we offer the possibility to achieve identical results without ever storing the pointwise map in memory.
Unlike many functional map learning methods, which use this algorithm at a post-processing step, ours can be easily used at train time.
arXiv Detail & Related papers (2024-03-30T12:01:04Z) - Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching [18.957179015912402]
We propose a novel unsupervised learning approach for non-rigid 3D shape matching.
We show that our method substantially outperforms previous state-of-the-art methods.
arXiv Detail & Related papers (2023-10-17T17:28:03Z) - Spatially and Spectrally Consistent Deep Functional Maps [26.203493922746546]
Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps within a collection of shapes.
In this paper, we investigate its utility in the approaches of Deep Functional Maps, which are considered state-of-the-art in non-rigid shape matching.
We present a novel design of unsupervised Deep Functional Maps, which effectively enforces the harmony of learned maps under the spectral and the point-wise representation.
arXiv Detail & Related papers (2023-08-17T09:04:44Z) - Unsupervised Learning of Robust Spectral Shape Matching [12.740151710302397]
We propose a novel learning-based approach for robust 3D shape matching.
Our method builds upon deep functional maps and can be trained in a fully unsupervised manner.
arXiv Detail & Related papers (2023-04-27T02:12:47Z) - Understanding and Improving Features Learned in Deep Functional Maps [31.61255365182462]
We show that features learned within deep functional map approaches can be used as point-wise descriptors across different shapes.
We propose effective modifications to the standard deep functional map pipeline, which promote structural properties of learned features.
arXiv Detail & Related papers (2023-03-29T08:32:16Z) - Multiway Non-rigid Point Cloud Registration via Learned Functional Map
Synchronization [105.14877281665011]
We present SyNoRiM, a novel way to register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.
We demonstrate via extensive experiments that our method achieves a state-of-the-art performance in registration accuracy.
arXiv Detail & Related papers (2021-11-25T02:37:59Z) - MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking [72.65494220685525]
We propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data.
We generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively.
To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target-driven attention mechanism.
arXiv Detail & Related papers (2021-07-22T03:10:51Z) - Compressing Deep ODE-Nets using Basis Function Expansions [105.05435207079759]
We consider formulations of the weights as continuous-depth functions using linear combinations of basis functions.
This perspective allows us to compress the weights through a change of basis, without retraining, while maintaining near state-of-the-art performance.
In turn, both inference time and the memory footprint are reduced, enabling quick and rigorous adaptation between computational environments.
arXiv Detail & Related papers (2021-06-21T03:04:51Z) - Deep Shells: Unsupervised Shape Correspondence with Optimal Transport [52.646396621449]
We propose a novel unsupervised learning approach to 3D shape correspondence.
We show that the proposed method significantly improves over the state-of-the-art on multiple datasets.
arXiv Detail & Related papers (2020-10-28T22:24:07Z) - iffDetector: Inference-aware Feature Filtering for Object Detection [70.8678270164057]
We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors.
IFF performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features.
IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead.
arXiv Detail & Related papers (2020-06-23T02:57:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.