Geodesic Models with Convexity Shape Prior

• URL: http://arxiv.org/abs/2111.00794v1
• Date: Mon, 1 Nov 2021 09:41:54 GMT
• Title: Geodesic Models with Convexity Shape Prior
• Authors: Da Chen and Jean-Marie Mirebeau and Minglei Shu and Xuecheng Tai and Laurent D. Cohen
• Abstract summary: In this paper, we take into account a more complicated problem: finding curvature-penalized geodesic paths with a convexity shape prior. We establish new geodesic models relying on the strategy of orientation-lifting. The convexity shape prior serves as a constraint for the construction of local geodesic metrics encoding a curvature constraint.
• Score: 8.932981695464761
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit image features in conjunction with geometric regularization terms, such as Euclidean curve length or curvature-penalized length, for computing geodesic curves. In this paper, we take into account a more complicated problem: finding curvature-penalized geodesic paths with a convexity shape prior. We establish new geodesic models relying on the strategy of orientation-lifting, by which a planar curve can be mapped to an high-dimensional orientation-dependent space. The convexity shape prior serves as a constraint for the construction of local geodesic metrics encoding a particular curvature constraint. Then the geodesic distances and the corresponding closed geodesic paths in the orientation-lifted space can be efficiently computed through state-of-the-art Hamiltonian fast marching method. In addition, we apply the proposed geodesic models to the active contours, leading to efficient interactive image segmentation algorithms that preserve the advantages of convexity shape prior and curvature penalization.

Related papers

• Learning Geodesics of Geometric Shape Deformations From Images [4.802048897896533]
  This paper presents a novel method, named geodesic deformable networks (GDN), that for the first time enables the learning of geodesic flows of deformation fields derived from images. In particular, the capability of our proposed GDN being able to predict geodesics is important for quantifying and comparing deformable shape presented in images.
  arXiv  Detail & Related papers  (2024-10-24T14:49:59Z)
• Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images [56.86175251327466]
  We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. Our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images.
  arXiv  Detail & Related papers  (2024-02-08T17:57:59Z)
• Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning [77.1421343649344]
  We propose a generalization of Transformers towards operating entirely on the product of constant curvature spaces. We also provide a kernelized approach to non-Euclidean attention, which enables our model to run in time and memory cost linear to the number of nodes and edges.
  arXiv  Detail & Related papers  (2023-09-08T02:44:37Z)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Short and Straight: Geodesics on Differentiable Manifolds [6.85316573653194]
  In this work, we first analyse existing methods for computing length-minimising geodesics. Second, we propose a model-based parameterisation for distance fields and geodesic flows on continuous manifold. Third, we develop a curvature-based training mechanism, sampling and scaling points in regions of the manifold exhibiting larger values of the Ricci scalar.
  arXiv  Detail & Related papers  (2023-05-24T15:09:41Z)
• First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces [93.35384756718868]
  min-max algorithms have been analyzed in the Euclidean setting. We prove that the extraiteient (RCEG) method corrected lastrate convergence at a linear rate.
  arXiv  Detail & Related papers  (2022-06-04T18:53:44Z)
• GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation [93.60478281489243]
  We propose a learnable network to approximate geodesic paths on 3D surfaces. The proposed method provides efficient approximations of the shortest paths and geodesic distances estimations.
  arXiv  Detail & Related papers  (2022-05-30T16:22:53Z)
• Geometric decomposition of geodesics and null phase curves using Majorana star representation [0.0]
  We use Majorana star representation to decompose a geodesic in the Hilbert space to $n-1$ curves on the Bloch sphere. We also propose a method to construct infinitely many NPCs between any two arbitrary states for $(n>2)$-dimensional Hilbert space.
  arXiv  Detail & Related papers  (2022-02-24T17:21:17Z)
• On Linear Interpolation in the Latent Space of Deep Generative Models [0.0]
  Smoothness and plausibility of linears in latent space are associated with the quality of the underlying generative model. We show that not all such curves are comparable as they can deviate arbitrarily from the shortest curve given by the geodesic. This deviation is revealed by computing curve lengths with the pull-back metric of the generative model.
  arXiv  Detail & Related papers  (2021-05-08T10:27:07Z)
• Convex Geometry and Duality of Over-parameterized Neural Networks [70.15611146583068]
  We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We show that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set. In higher dimensions, we show that the training problem can be cast as a finite dimensional convex problem with infinitely many constraints.
  arXiv  Detail & Related papers  (2020-02-25T23:05:33Z)
• A Region-based Randers Geodesic Approach for Image Segmentation [16.091797508701045]
  We introduce a new variational image segmentation model based on the minimal geodesic path framework. We also suggest a practical interactive image segmentation strategy, where the target boundary can be delineated by the concatenation of several piecewise geodesic paths.
  arXiv  Detail & Related papers  (2019-12-20T22:17:50Z)

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.