Weighted Mean Curvature
In image processing tasks, spatial priors are essential for robust computations, regularization, algorithmic design and Bayesian inference. In this paper, we introduce weighted mean curvature (WMC) as a novel image prior and present an efficient computation scheme for its discretization in practical image processing applications. We first demonstrate the favorable properties of WMC, such as sampling invariance, scale invariance, and contrast invariance with Gaussian noise model; and we show the relation of WMC to area regularization. We further propose an efficient computation scheme for discretized WMC, which is demonstrated herein to process over 33.2 giga-pixels/second on GPU. This scheme yields itself to a convolutional neural network representation. Finally, WMC is evaluated on synthetic and real images, showing its superiority quantitatively to total-variation and mean curvature.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceGPUSimilar Papers 제목 키워드 기반
A Discrete Scheme for Computing Image's Weighted Gaussian Curvature
Weighted Gaussian Curvature is an important measurement for images. However, its conventional computation scheme has low performance, low accuracy and requires that the input image must be second order differentiable. To…
image smoothingOptical Flow EstimationCurvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs
Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularity and spectral methods are feature agnostic, while deep grap…
Community DetectionDiscrete scalar curvature as a weighted sum of Ollivier-Ricci curvatures
We study the relationship between discrete analogues of Ricci and scalar curvature that are defined for point clouds and graphs. In the discrete setting, Ricci curvature is replaced by Ollivier-Ricci curvature. Scalar cu…
Point CloudsA mean curvature flow arising in adversarial training
We connect adversarial training for binary classification to a geometric evolution equation for the decision boundary. Relying on a perspective that recasts adversarial training as a regularization problem, we introduce …
Binary ClassificationActive Contour Models Driven by Hyperbolic Mean Curvature Flow for Image Segmentation
Parabolic mean curvature flow-driven active contour models (PMCF-ACMs) are widely used in image segmentation, which however depend heavily on the selection of initial curve configurations. In this paper, we firstly propo…
Image SegmentationSemantic Segmentation