arXiv subjects

Hoon Hwangbo

Publications and source records attributed to Hoon Hwangbo.

4 recordsLinked to original sources

arXiv2023

A Comprehensive Survey on Deep Neural Image Deblurring

Image deblurring tries to eliminate degradation elements of an image causing blurriness and improve the quality of an image for better texture and object visualization. Traditionally, prior-based optimization approaches predominated in image deblurring, but deep neural networks recently brought a major breakthrough in the field. In this paper, we comprehensively review the recent progress of the deep neural architectures in both blind and non-blind image deblurring. We outline the most popular deep neural network structures used in deblurring applications, describe their strengths and novelties, summarize performance metrics, and introduce broadly used datasets. In addition, we discuss the current challenges and research gaps in this domain and suggest potential research directions for future works.

cs.CV↗

arXiv2021

A Subspace-based Approach for Dimensionality Reduction and Important Variable Selection

An analysis of high-dimensional data can offer a detailed description of a system but is often challenged by the curse of dimensionality. General dimensionality reduction techniques can alleviate such difficulty by extracting a few important features, but they are limited due to the lack of interpretability and connectivity to actual decision making associated with each physical variable. Variable selection techniques, as an alternative, can maintain the interpretability, but they often involve a greedy search that is susceptible to failure in capturing important interactions or a metaheuristic search that requires extensive computations. This research proposes a new method that produces subspaces, reduced-dimensional physical spaces, based on a randomized search and leverages an ensemble of critical subspace-based models, achieving dimensionality reduction and variable selection. When applied to high-dimensional data collected from the failure prediction of a composite/metal hybrid structure exhibiting complex progressive damage failure under loading, the proposed method outperforms the existing and potential alternatives in prediction and important variable selection.

stat.ME↗

arXiv2021

Blind Image Deblurring based on Kernel Mixture

Blind Image deblurring tries to estimate blurriness and a latent image out of a blurred image. This estimation, as being an ill-posed problem, requires imposing restrictions on the latent image or a blur kernel that represents blurriness. Different from recent studies that impose some priors on the latent image, this paper regulates the structure of the blur kernel. We propose a kernel mixture structure while using the Gaussian kernel as a base kernel. By combining multiple Gaussian kernels structurally enhanced in terms of scales and centers, the kernel mixture becomes capable of modeling nearly non-parametric shape of blurriness. A data-driven decision for the number of base kernels to combine makes the structure even more flexible. We apply this approach to a remote sensing problem to recover images from blurry images of satellite. This case study shows the superiority of the proposed method regulating the blur kernel in comparison with state-of-the-art methods that regulates the latent image.

cs.CV↗

arXiv2019

Machine Learning Based Analysis and Quantification of Potential Power Gain from Passive Device Installation

Passive device installation on wind turbine generators (WTGs) can potentially improve the power generation of WTGs. Yet, how much impact the installation will make is unclear because conducting controlled experiments is impossible due to ever-changing wind and weather that affect the power generation significantly. In addition, the potential improvement is believed to be in a small scale, such as 1-5%, which is less than a typical 3-8% variation level observed in wind data. This article proposes an adaptive kernel-based method and builds a surrogate model to reduce the level of unexplained variation in wind data. In addition, to establish experimental environments that are similar to a controlled situation, this article develops an analysis framework that utilizes two other nearby WTGs without any passive device installation.

stat.AP↗