An official website of the United States government
The reconstruction of a discrete surface from a point cloud is a fundamental geometry processing problem that has been studied for decades, with many methods developed. We propose the use of a deep neural network as a geometric prior for surface reconstruction. Specifically, we overfit a neural network representing a local chart parameterization to part of an input point cloud using the Wasserstein distance as a measure of approximation. By jointly fitting many such networks to overlapping parts of the point cloud, while enforcing a consistency condition, we compute a manifold atlas. By sampling this atlas, we can produce a dense reconstruction of the surface approximating the input cloud. The entire procedure does not require any training data or explicit regularization, yet, we show that it is able to perform remarkably well: not introducing typical overfitting artifacts, and approximating sharp features closely at the same time. We experimentally show that this geometric prior produces good results for both man-made objects containing sharp features and smoother organic objects, as well as noisy inputs. We compare our method with a number of well-known reconstruction methods on a standard surface reconstruction benchmark.
more »
« less
Microlocal analysis of borehole seismic data
Borehole seismic data is obtained by receivers located in a well, with sources located on the surface or another well. Using microlocal analysis, we study possible approximate reconstruction, via linearized, filtered backprojection, of an isotropic sound speed in the subsurface for three types of data sets. The sources may form a dense array on the surface, or be located along a line on the surface (walkaway geometry) or in another borehole (crosswell). We show that for the dense array, reconstruction is feasible, with no artifacts in the absence of caustics in the background ray geometry, and mild artifacts in the presence of fold caustics in a sense that we define. In contrast, the walkaway and crosswell data sets both give rise to strong, nonremovable artifacts.
more »
« less
- Award ID(s):
- 1906186
- PAR ID:
- 10333419
- Date Published:
- Journal Name:
- Inverse Problems and Imaging
- Volume:
- 0
- Issue:
- 0
- ISSN:
- 1930-8337
- Page Range / eLocation ID:
- 0
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The reconstruction of a discrete surface from a point cloud is a fundamental geometry processing problem that has been studied for decades, with many methods developed. We propose the use of a deep neural network as a geometric prior for surface reconstruction. Specifically, we overfit a neural network representing a local chart parameterization to part of an input point cloud using the Wasserstein distance as a measure of approximation. By jointly fitting many such networks to overlapping parts of the point cloud, while enforcing a consistency condition, we compute a manifold atlas. By sampling this atlas, we can produce a dense reconstruction of the surface approximating the input cloud. The entire procedure does not require any training data or explicit regularization, yet, we show that it is able to perform remarkably well: not introducing typical overfitting artifacts, and approximating sharp features closely at the same time. We experimentally show that this geometric prior produces good results for both man-made objects containing sharp features and smoother organic objects, as well as noisy inputs. We compare our method with a number of well-known reconstruction methods on a standard surface reconstruction benchmark.more » « less
-
Social science approaches to missing values predict avoided, unrequested, or lost information from dense data sets, typically surveys. The authors propose a matrix factorization approach to missing data imputation that (1) identifies underlying factors to model similarities across respondents and responses and (2) regularizes across factors to reduce their overinfluence for optimal data reconstruction. This approach may enable social scientists to draw new conclusions from sparse data sets with a large number of features, for example, historical or archival sources, online surveys with high attrition rates, or data sets created from Web scraping, which confound traditional imputation techniques. The authors introduce matrix factorization techniques and detail their probabilistic interpretation, and they demonstrate these techniques’ consistency with Rubin’s multiple imputation framework. The authors show via simulations using artificial data and data from real-world subsets of the General Social Survey and National Longitudinal Study of Youth cases for which matrix factorization techniques may be preferred. These findings recommend the use of matrix factorization for data reconstruction in several settings, particularly when data are Boolean and categorical and when large proportions of the data are missing.more » « less
-
Self‐supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (MRI) reconstruction methods without fully sampled data. Current self‐supervised learning methods for physics‐guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network, while the other is used to define the training loss. In this study, we propose an improved self‐supervised learning strategy that more efficiently uses the acquired data to train a physics‐guided reconstruction network without a database of fully sampled data. The proposed multi‐mask self‐supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi‐mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG‐SENSE, and single‐mask SSDU DL‐MRI, as well as supervised DL‐MRI when fully sampled data are available. The results on knee MRI show that the proposed multi‐mask SSDU outperforms SSDU and performs as well as supervised DL‐MRI. A clinical reader study further ranks the multi‐mask SSDU higher than supervised DL‐MRI in terms of signal‐to‐noise ratio and aliasing artifacts. Results on brain MRI show that multi‐mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi‐mask SSDU at R = 8 significantly improves reconstruction compared with single‐mask SSDU at R = 8, as well as CG‐SENSE at R = 2.more » « less
-
Abstract Distributed acoustic sensing (DAS) provides dense arrays ideal for seismic tomography. However, DAS only records average axial strain change along the cable, which can complicate the interpretation of surface-wave observations. With a rectangular DAS array located in the City of Oxnard, California, we compare phase velocity dispersion at the same location illuminated by differently oriented virtual sources. The dispersion curves are consistent for colinear and noncolinear virtual sources, suggesting that surface-wave observations in most of the cross-correlations are dominated by Rayleigh waves. Our measurements confirm that colinear channel pairs provide higher Rayleigh-wave signal-to-noise ratio (SNR). For cross-correlations of noncolinear channel pairs, the travel time of each connecting ray path can still be obtained despite the lower SNR of Rayleigh wave signals. The inverted Rayleigh-wave dispersion map reveals an ancient river channel consistent with the local geologic map. Our results demonstrate the potential of DAS-based 2D surface-wave tomography without special treatment of directional sensitivity in areas where one type of wave is dominating or can be identified.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3934/ipi.2022026
