paper-with-me

홈 › Papers

Combining Contrast Invariant L1 Data Fidelities with Nonlinear Spectral Image Decomposition

2017-03-16 · Leonie Zeune, Stephan A. van Gils, Leon W. M. M. Terstappen, Christoph Brune

This paper focuses on multi-scale approaches for variational methods and corresponding gradient flows. Recently, for convex regularization functionals such as total variation, new theory and algorithms for nonlinear eigenvalue problems via nonlinear spectral decompositions have been developed. Those methods open new directions for advanced image filtering. However, for an effective use in image segmentation and shape decomposition, a clear interpretation of the spectral response regarding size and intensity scales is needed but lacking in current approaches. In this context, $L^1$ data fidelities are particularly helpful due to their interesting multi-scale properties such as contrast invariance. Hence, the novelty of this work is the combination of $L^1$-based multi-scale methods with nonlinear spectral decompositions. We compare $L^1$ with $L^2$ scale-space methods in view of spectral image representation and decomposition. We show that the contrast invariant multi-scale behavior of $L^1-TV$ promotes sparsity in the spectral response providing more informative decompositions. We provide a numerical method and analyze synthetic and biomedical images at which decomposition leads to improved segmentation.

📄 PDF Abstract BibTeX arXiv:1703.05560

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Multi-Fidelity High-Order Gaussian Processes for Physical Simulation

2020-06-08 · Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

The key task of physical simulation is to solve partial differential equations (PDEs) on discretized domains, which is known to be costly. In particular, high-fidelity solutions are much more expensive than low-fidelity …

Gaussian ProcessesVocal Bursts Intensity Prediction

Scaled Relative Graph Analysis of Lur'e Systems and the Generalized Circle Criterion

2024-11-27 · Julius P. J. Krebbekx, Roland Tóth, Amritam Das

Scaled Relative Graphs (SRGs) provide a novel graphical frequency-domain method for the analysis of nonlinear systems. However, we show that the current SRG analysis suffers from a pitfall that limit its applicability in…

LInK: Learning Joint Representations of Design and Performance Spaces through Contrastive Learning for Mechanism Synthesis

2024-05-31 · Amin Heyrani Nobari, Akash Srivastava, Dan Gutfreund, Kai Xu 외

In this paper, we introduce LInK, a novel framework that integrates contrastive learning of performance and design space with optimization techniques for solving complex inverse problems in engineering design with discre…

Contrastive Learning

Structure-Preserving Physics-Informed Neural Network for the Korteweg--de Vries (KdV) Equation

2025-11-01 · Victory Obieke, Emmanuel Oguadimma arxiv

Physics-Informed Neural Networks (PINNs) offer a flexible framework for solving nonlinear partial differential equations (PDEs), yet conventional implementations often fail to preserve key physical invariants during long…

Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling

2024-02-29 · Ruijia Niu, Dongxia Wu, Kai Kim, Yi-An Ma 외

Multi-fidelity surrogate modeling aims to learn an accurate surrogate at the highest fidelity level by combining data from multiple sources. Traditional methods relying on Gaussian processes can hardly scale to high-dime…

DecoderGaussian Processes