Unsupervised Dense Shape Correspondence using Heat Kernels

• URL: http://arxiv.org/abs/2010.12682v1
• Date: Fri, 23 Oct 2020 21:54:10 GMT
• Title: Unsupervised Dense Shape Correspondence using Heat Kernels
• Authors: Mehmet Ayg\"un, Zorah L\"ahner, Daniel Cremers
• Abstract summary: We propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework. Instead of depending on ground-truth correspondences or the computationally expensive geodesic distances, we use heat kernels. We present the results of our method on different benchmarks which have various challenges like partiality, topological noise and different connectivity.
• Score: 50.682560435495034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework. Instead of depending on ground-truth correspondences or the computationally expensive geodesic distances, we use heat kernels. These can be computed quickly during training as the supervisor signal. Moreover, we propose a curriculum learning strategy using different heat diffusion times which provide different levels of difficulty during optimization without any sampling mechanism or hard example mining. We present the results of our method on different benchmarks which have various challenges like partiality, topological noise and different connectivity.

Related papers

• Learning the Geodesic Embedding with Graph Neural Networks [22.49236293942187]
  We present GeGnn, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude.
  arXiv  Detail & Related papers  (2023-09-11T16:54:34Z)
• Score-based Data Assimilation [7.215767098253208]
  We introduce score-based data assimilation for trajectory inference. We learn a score-based generative model of state trajectories based on the key insight that the score of an arbitrarily long trajectory can be decomposed into a series of scores over short segments.
  arXiv  Detail & Related papers  (2023-06-18T14:22:03Z)
• A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction [66.21060114843202]
  We propose a more general heat kernel based manifold embedding method that we call heat geodesic embeddings. Results show that our method outperforms existing state of the art in preserving ground truth manifold distances. We also showcase our method on single cell RNA-sequencing datasets with both continuum and cluster structure.
  arXiv  Detail & Related papers  (2023-05-30T13:58:50Z)
• LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning [17.571160136568455]
  We propose a novel approach that looks for optimal hard negatives (LoOp) in the embedding space. Unlike mining-based methods, our approach considers the entire space between pairs of embeddings to calculate the optimal hard negatives.
  arXiv  Detail & Related papers  (2021-08-20T19:21:33Z)
• Uniform Sampling over Episode Difficulty [55.067544082168624]
  We propose a method to approximate episode sampling distributions based on their difficulty. As the proposed sampling method is algorithm agnostic, we can leverage these insights to improve few-shot learning accuracies.
  arXiv  Detail & Related papers  (2021-08-03T17:58:54Z)
• A Detector-oblivious Multi-arm Network for Keypoint Matching [14.051194519908455]
  We propose a Multi-Arm Network (MAN) to learn region overlap and depth. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-02T08:55:04Z)
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning [63.354671267760516]
  We propose the concept of implicit manifold learning, where manifold information is implicitly obtained by learning the associated heat kernel. The learned heat kernel can be applied to various kernel-based machine learning models, including deep generative models (DGM) for data generation and Stein Variational Gradient Descent for Bayesian inference.
  arXiv  Detail & Related papers  (2020-10-05T03:39:58Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• Learning with Differentiable Perturbed Optimizers [54.351317101356614]
  We propose a systematic method to transform operations into operations that are differentiable and never locally constant. Our approach relies on perturbeds, and can be used readily together with existing solvers. We show how this framework can be connected to a family of losses developed in structured prediction, and give theoretical guarantees for their use in learning tasks.
  arXiv  Detail & Related papers  (2020-02-20T11:11:32Z)

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.