Understanding and Improving Features Learned in Deep Functional Maps

• URL: http://arxiv.org/abs/2303.16527v1
• Date: Wed, 29 Mar 2023 08:32:16 GMT
• Title: Understanding and Improving Features Learned in Deep Functional Maps
• Authors: Souhaib Attaiki and Maks Ovsjanikov
• Abstract summary: 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.
• Score: 31.61255365182462
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep functional maps have recently emerged as a successful paradigm for non-rigid 3D shape correspondence tasks. An essential step in this pipeline consists in learning feature functions that are used as constraints to solve for a functional map inside the network. However, the precise nature of the information learned and stored in these functions is not yet well understood. Specifically, a major question is whether these features can be used for any other objective, apart from their purely algebraic role in solving for functional map matrices. In this paper, we show that under some mild conditions, the features learned within deep functional map approaches can be used as point-wise descriptors and thus are directly comparable across different shapes, even without the necessity of solving for a functional map at test time. Furthermore, informed by our analysis, we propose effective modifications to the standard deep functional map pipeline, which promote structural properties of learned features, significantly improving the matching results. Finally, we demonstrate that previously unsuccessful attempts at using extrinsic architectures for deep functional map feature extraction can be remedied via simple architectural changes, which encourage the theoretical properties suggested by our analysis. We thus bridge the gap between intrinsic and extrinsic surface-based learning, suggesting the necessary and sufficient conditions for successful shape matching. Our code is available at https://github.com/pvnieo/clover.

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)
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models [55.19497659895122]
  We introduce methods for discovering and applying sparse feature circuits. These are causally implicatedworks of human-interpretable features for explaining language model behaviors.
  arXiv  Detail & Related papers  (2024-03-28T17:56:07Z)
• Deep Frequency-Aware Functional Maps for Robust Shape Matching [17.276162941967943]
  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.
  arXiv  Detail & Related papers  (2024-02-06T11:16:18Z)
• 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)
• 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)
• Neural Eigenfunctions Are Structured Representation Learners [93.53445940137618]
  This paper introduces a structured, adaptive-length deep representation called Neural Eigenmap. We show that, when the eigenfunction is derived from positive relations in a data augmentation setup, applying NeuralEF results in an objective function. We demonstrate using such representations as adaptive-length codes in image retrieval systems.
  arXiv  Detail & Related papers  (2022-10-23T07:17:55Z)
• Learning Implicit Feature Alignment Function for Semantic Segmentation [51.36809814890326]
  Implicit Feature Alignment function (IFA) is inspired by the rapidly expanding topic of implicit neural representations. We show that IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions. Our method can be combined with improvement on various architectures, and it achieves state-of-the-art accuracy trade-off on common benchmarks.
  arXiv  Detail & Related papers  (2022-06-17T09:40:14Z)
• 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)
• Correspondence Learning via Linearly-invariant Embedding [40.07515336866026]
  We show that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings. We demonstrate that our approach achieves state-of-the-art results in challenging non-rigid 3D point cloud correspondence applications.
  arXiv  Detail & Related papers  (2020-10-25T15:31:53Z)
• Image Matching across Wide Baselines: From Paper to Practice [80.9424750998559]
  We introduce a comprehensive benchmark for local features and robust estimation algorithms. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods. We show that with proper settings, classical solutions may still outperform the perceived state of the art.
  arXiv  Detail & Related papers  (2020-03-03T15:20:57Z)

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.