4.6 Article

Three-Dimensional Surface Reconstruction from Point Clouds Using Euler's Elastica Regularization

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Elastica Models for Color Image Regularization

Hao Liu et al.

Summary: The choice of a proper regularization measure is crucial in image processing. One classical approach treats color images as two-dimensional surfaces embedded in a five-dimensional spatial-chromatic space, where the image surface area naturally serves as a regularization term. By considering the chromatic coordinates as dominating over the spatial ones, the image spatial coordinates can be regarded as a parameterization of the image surface manifold in a three-dimensional color space. Minimizing the area of the image manifold leads to the Beltrami flow or mean curvature flow of the image surface in the three-dimensional color space, while minimizing the elastica of the image surface provides an interesting regularization.

SIAM JOURNAL ON IMAGING SCIENCES (2023)

Proceedings Paper Computer Science, Artificial Intelligence

IterativePFN: True Iterative Point Cloud Filtering

Dasith de Silva Edirimuni et al.

Summary: The quality of point clouds is often limited by noise, and removing noise through filtering or denoising is a fundamental task in 3D vision. The proposed IterativePFN network models the iterative filtering process internally and trains using a novel loss function, resulting in faster convergence to clean surfaces compared to state-of-the-art methods.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2023)

Article Mathematics, Applied

Image Multiplicative Denoising Using Adaptive Euler's Elastica as the Regularization

Yu Zhang et al.

Summary: In this paper, a novel multiplicative noise removal model based on adaptive Euler's elastica is proposed for the denoising problem. Two fast numerical algorithms are developed to solve the model, and numerical experiments demonstrate the effectiveness of the algorithms.

JOURNAL OF SCIENTIFIC COMPUTING (2022)

Article Multidisciplinary Sciences

New dual method for elastica regularization

Jintao Song et al.

Summary: This paper proposes a new dual method to simplify the solver for Euler's elastica energy regularizer, which is widely used in image processing and computer vision tasks. The proposed method accurately maintains the constraint with only one dual parameter, making it suitable for level-set-based segmentation models.

PLOS ONE (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling

Xumin Yu et al.

Summary: Point-BERT is a new paradigm that extends the concept of BERT to 3D point cloud. Through pre-training and task-specific strategies, Point-BERT significantly improves the performance in point cloud classification and transfer learning tasks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

Baorui Ma et al.

Summary: This article introduces a method for reconstructing surfaces from sparse point clouds. By training a neural network to learn the Signed Distance Functions (SDFs) and utilizing on-surface prior to determine points on the surface, it achieves highly accurate surface reconstruction.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

An Elastica Geodesic Approach with Convexity Shape Prior

Da Chen et al.

Summary: The minimal geodesic models based on the Eikonal equations prove capable of addressing various image segmentation scenarios by incorporating a convexity shape prior and region-based homogeneity features. The proposed approach utilizes an orientation-lifting strategy and fast marching method for efficient computation of geodesic curves in a high-dimensional orientation space. This method provides solutions for segmentation issues with shape prior constraints.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Article Computer Science, Artificial Intelligence

A Color Elastica Model for Vector-Valued Image Regularization

Hao Liu et al.

Summary: This paper introduces an extension method for the Polyakov action for color images, which processes color images by minimizing the color manifold curvature. The proposed model decouples nonlinearity, converts the problem into solving for the steady state of the initial-value problem, and uses a time-splitting approach to obtain closed-form solutions, demonstrating the efficiency and robustness of the method through systematic numerical experiments.

SIAM JOURNAL ON IMAGING SCIENCES (2021)

Article Geography, Physical

Robust 3D reconstruction of building surfaces from point clouds based on structural and closed constraints

Senyuan Wang et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2020)

Article Computer Science, Artificial Intelligence

Curvature Regularized Surface Reconstruction from Point Clouds

Yuchen He et al.

SIAM JOURNAL ON IMAGING SCIENCES (2020)

Proceedings Paper Computer Science, Artificial Intelligence

`Deep Geometric Prior for Surface Reconstruction

Francis Williams et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Computer Science, Artificial Intelligence

Surface reconstruction from unorganized points with l(0) gradient minimization

Huibin Li et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2018)

Article Mathematics, Applied

Robust and Efficient Implicit Surface Reconstruction for Point Clouds Based on Convexified Image Segmentation

Jian Liang et al.

JOURNAL OF SCIENTIFIC COMPUTING (2013)

Article Mathematics, Applied

Image Segmentation Using Euler's Elastica as the Regularization

Wei Zhu et al.

JOURNAL OF SCIENTIFIC COMPUTING (2013)

Article Computer Science, Artificial Intelligence

A Fast Algorithm for Euler's Elastica Model Using Augmented Lagrangian Method

Xue-Cheng Tai et al.

SIAM JOURNAL ON IMAGING SCIENCES (2011)

Article Computer Science, Artificial Intelligence

Fast global minimization of the active Contour/Snake model

Xavier Bresson et al.

JOURNAL OF MATHEMATICAL IMAGING AND VISION (2007)

Article Mathematics, Applied

Algorithms for finding global minimizers of image segmentation and denoising models

Tony F. Chan et al.

SIAM JOURNAL ON APPLIED MATHEMATICS (2006)

Article Mathematics, Applied

Fast sweeping algorithms for a class of Hamilton-Jacobi equations

YHR Tsai et al.

SIAM JOURNAL ON NUMERICAL ANALYSIS (2003)

Article Computer Science, Artificial Intelligence

Implicit and nonparametric shape reconstruction from unorganized data using a variational level set method

HK Zhao et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2000)