Zhongxuan Luo

Dalian University of Technology | DUT · School of Software

Underwater communication has been a focal point of communication research, driven by a multitude of applications including underwater facility maintenance and marine exploration. However, current systems often require expensive specialized equipment, rendering them less accessible. In this paper, we break the norm by pioneering the use of Commercia...

Short text clustering is a significant yet challenging task, where short texts generated from the Internet are extremely sparse, noisy, and ambiguous. The sparse nature makes traditional clustering methods, e.g.,k-means family and topic modeling, much less effective. Fortunately, recent arts of document distance, e.g., word mover’s distance, and do...

In recent years, the knowledge surrounding diffusion models(DMs) has grown significantly, though several theoretical gaps remain. Particularly noteworthy is prior error, defined as the discrepancy between the termination distribution of the forward process and the initial distribution of the reverse process. To address these deficiencies, this pape...

Optimal transport (OT) studies the most economical transformation of one probability measure into another, attracting attention across diverse fields and inspiring various OT-solving algorithms. However, adjusting the probability measure according to specific application requirements, such as achieving unbiased generated images or generating images...

Joint injuries, and their long-term consequences, present a substantial global health burden. Wearable prophylactic braces are an attractive potential solution to reduce the incidence of joint injuries by limiting joint movements that are related to injury risk. Given human motion and ground reaction forces, we present a computational framework tha...

In this paper, we construct a new mixed finite element for the Stokes problem on general convex quadrilateral partitions. The velocity is approximated by piecewise polynomial element space, and the pressure is approximated by piecewise constant. Moreover, we assert that the discrete velocity is second-order convergent in discrete \(H^{1}\) seminorm...

Texture mapping is a common technology in the area of computer graphics, it maps the 3D surface space onto the 2D texture space. However, the loose texture space will reduce the efficiency of data storage and GPU memory addressing in the rendering process. Many of the existing methods focus on repacking given textures, but they still suffer from hi...

Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore,...

With the widespread application of optimal transport (OT), its calculation becomes essential, and various algorithms have emerged. However, the existing methods either have low efficiency or cannot represent discontinuous maps. A novel reusable neural OT solver OT-Net is thus presented, which first learns Brenier’s height representation via the neu...

Infrared and visible image fusion targets to provide an informative image by combining complementary information from different sensors. Existing learning-based fusion approaches attempt to construct various loss functions to preserve complementary features, while neglecting to discover the inter-relationship between the two modalities, leading to...

In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate image/feature propagation. There is a lack of the unified consideration to construct propagative modules, provide theoreti...

Underwater object detection suffers from low detection performance because the distance and wavelength dependent imaging process yield evident image quality degradations such as haze-like effects, low visibility, and color distortions. Therefore, we commit to resolving the issue of underwater object detection with compounded environmental degradati...

Efficiently optimizing the internal structure of 3D printing models is a critical focus in the field of industrial manufacturing, particularly when designing self‐supporting structures that offer high stiffness and lightweight characteristics. To tackle this challenge, this research introduces a novel approach featuring a self‐supporting polyhedral...

Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before...

Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimization or deep networks, requires tremendous efforts from computer experts to well design registration energy or to carefully tune network architectures with respect to me...

Underwater object detection suffers from low detection performance because the distance and wavelength dependent imaging process yield evident image quality degradations such as haze-like effects, low visibility, and color distortions. Therefore, we commit to resolving the issue of underwater object detection with compounded environmental degradati...

Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by...

Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, \emph{e.g.,} fusion or segmentation, making it hard to reach~`Best of Both Worlds'. To overcome this issue, in this paper, we propose a \textbf{M}ulti-\textbf{i}nteractive \te...

Sampling from diffusion probabilistic models (DPMs) can be viewed as a piecewise distribution transformation, which generally requires hundreds or thousands of steps of the inverse diffusion trajectory to get a high-quality image. Recent progress in designing fast samplers for DPMs achieves a trade-off between sampling speed and sample quality by k...

With the widespread application of optimal transport (OT), its calculation becomes essential, and various algorithms have emerged. However, the existing methods either have low efficiency or cannot represent discontinuous maps. A novel reusable neural OT solver OT-Net is thus presented, which first learns Brenier's height representation via the neu...

Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore,...

Triply Periodic Minimal Surface (TPMS) is suitable for the heat transfer of fluids, but it is difficult to preserve the integrality of independent fluids channels during optimization. We present an effective meshless optimization framework of Triply Periodic Minimal Surface based two-fluid heat exchangers, which can be represented, analyzed and opt...

It is challenging to characterize the intrinsic geometry of high-degree algebraic curves with lower-degree algebraic curves. The reduction in the curve’s degree implies lower computation costs, which is crucial for various practical computer vision systems. In this paper, we develop a characteristic mapping (CM) to recursively degenerate $\mathbf...

We propose a new method to generate surface quadrilateral mesh by calculating a globally defined parameterization with feature constraints. In the field of quadrilateral generation with features, the cross field methods are well-known because of their superior performance in feature preservation. The methods based on metrics are popular due to thei...

Designing thin-shell structures that are diverse, lightweight, and physically viable is a challenging task for traditional heuristic methods. To address this challenge, we present a novel parametric design framework for engraving regular, irregular, and customized patterns on thin-shell structures. Our method optimizes pattern parameters such as si...

In this paper, we focus on the redesign of the output layer for the weighted regularized extreme learning machine (WRELM). For multi-classification problems, the conventional method of the output layer setting, named “one-hot method”, is as follows: Let the class of samples be r; then, the output layer node number is r and the ideal output of s-th...

Improving the visual quality of the given degraded observation by correcting exposure level is a fundamental task in the computer vision community. Existing works commonly lack adaptability towards unknown scenes because of the data-driven patterns (deep networks) and limited regularization (traditional optimization), and they usually need time-con...

Infrared and visible image fusion targets to provide an informative image by combining complementary information from different sensors. Existing learning-based fusion approaches attempt to construct various loss functions to preserve complementary features from both modalities, while neglecting to discover the inter-relationship between the two mo...

Recent advances in deep networks have gained great attention in infrared and visible image fusion (IVIF). Nevertheless, most existing methods are incapable of dealing with slight misalignment on source images and suffer from high computational and spatial expenses. This paper tackles these two critical issues rarely touched in the community by deve...

Affine registration aims to find the low-dimensional parametric transformation that best aligns one data to another. However, existing registration methods, either classic energy optimization or deep learning are mainly designed for adult brain images and have limited performance on infant brain images with widely varied intensity distributions and...

Images captured from low-light scenes often suffer from severe degradations, including low visibility, color casts, intensive noises, etc. These factors not only degrade image qualities, but also affect the performance of downstream Low-Light Vision (LLV) applications. A variety of deep networks have been proposed to enhance the visual quality of l...

In this paper, we conduct a comprehensive study of Underwater Object Detection (UOD). UOD has evolved into an attractive research field in the computer vision community in recent years. However, existing UOD datasets collected from specific underwater scenes are limited in the number of images, categories, resolution, and environmental challenges....

We propose a simple nonconforming rectangular finite element method for the Brinkman model. The velocity space is edge-oriented, in which the local space of each component is \(P_2\) plus the span of a cubic monomial, and the pressure space is piecewise linear. We prove that, if the mesh is uniform, this method is uniformly convergent with respect...

Existing fine-grained image recognition methods are difficult to learn complete discriminative features from low-resolution (LR) data, because the original subtle inter-class distinctions become slimmer with the reduction of the image resolution. Besides, existing methods of LR fine-grained image recognition and general LR image recognition only co...

Image denoising is an issue of intensive research in the image processing community. As the wave of deep learning advances, image denoising with convolutional neural networks has recently made drastic progress, however, they usually can not recover atypical details from noisy images. Motivated by the above, we propose a multiview texture-aware conv...

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-...

Short text clustering is a significant yet challenging task, where short texts generated from the Internet are extremely sparse, noisy, and ambiguous. The sparse nature makes traditional clustering methods, e.g., k-means family and topic model-ing, much less effective. Fortunately, recent arts of document distance, e.g., word mover’s distance, and...

This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that mo...

Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimization or deep networks requires tremendous efforts from computer experts to well design registration energy or to carefully tune network architectures for the specific ty...

The existing methods of fine-grained image recognition mainly devote to learning subtle yet discriminative features from the high-resolution input. However, their performance deteriorates significantly when they are used for low quality images because a lot of discriminative details of images are missing. We propose a discriminative information res...

Structured meshes play crucial roles in engineering fields. This work studies the configurations of singular vertices on structured meshes based on Abel-Jacobi theory. It discovers the fundamental relations between the structured meshes and the meromorphic differentials, and give a unified, simpler proof for the non-existence of some structured mes...

Optimal transportation plays an important role in many engineering fields, especially in deep learning. By the Brenier theorem, computing optimal transportation maps is reduced to solving Monge-Ampère equations, which in turn is equivalent to constructing Alexandrov polytopes. Furthermore, the regularity theory of Monge-Ampère equation explains mod...

In this paper, a novel smooth group L1/2 (SGL1/2) regularization method is proposed for pruning hidden nodes of the fully connected layer in convolution neural networks. Usually, the selection of nodes and weights is based on experience, and the convolution filter is symmetric in the convolution neural network. The main contribution of SGL1/2 is to...

Low-light image enhancement aims to improve the quality of images captured under low-lightening conditions, which is a fundamental problem in computer vision and multimedia areas. Although many efforts have been invested over the years, existing illumination-based models tend to generate unnatural-looking results (e.g., over-exposure). It is becaus...

In this work, we establish a regularity theory for the optimal transport problem when the target is composed of two disjoint convex domains, denoted $\Omega^*_i$ for $i=1, 2$. This is a fundamental model in which singularities arise. Even though the singular set does not exhibit any form of convexity a priori, we are able to prove its higher order...

Images captured from low-light scenes often suffer from severe degradations, including low visibility, color cast and intensive noises, etc. These factors not only affect image qualities, but also degrade the performance of downstream Low-Light Vision (LLV) applications. A variety of deep learning methods have been proposed to enhance the visual qu...

Enhancing the quality of low-light images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-leve...

In this paper, we present an effective prismatic mesh generation method for viscous flow simulations. To address the prismatic mesh collisions in recessed cavities or slit areas, we exploit 3D tensors controlled anisotropic volume harmonic field to generate prismatic meshes. Specially, a well-fitting tetrahedral mesh is first constructed to serve a...

This work proposes a rigorous and practical algorithm for quad-mesh generation based the Abel–Jacobi theory of algebraic curves. We prove sufficient and necessary conditions for a flat metric with cone singularities to be compatible with a quad-mesh, in terms of the deck-transformation, then develop an algorithm based on the theorem. The algorithm...

We present a function representation based analytic optimization framework for shape hollowing problem to achieve various functionalities. A compact description of model with cavities is constructed by introducing a field function, which could handle geometry and topology changes of interior shapes effortlessly without both local and global self-in...

Recently, underwater image enhancement has attracted broad attention due to its potential in ocean exploitation. Unfortunately, limited to the hand-crafted subjective ground truth for matching low-quality underwater images, existing techniques are less robust for some unseen scenarios and may be unfriendly to semantic-related vision tasks. To handl...

Existing deep learning-based video deraining techniques have achieved remarkable processes. However, there exist some fundamental issues including plentiful engineering experiences for architecture design and slow hardware-insensitive inference speed. To settle these issues, we develop a highly efficient spatial-temporal aggregated video deraining...

Conventional deformable registration methods aim at solving an optimization model carefully designed on image pairs and their computational costs are exceptionally high. In contrast, recent deep learning-based approaches can provide fast deformation estimation. These heuristic network architectures are fully data-driven and thus lack explicit geome...

A new nonparametric nonconforming quadrilateral finite element is used to approximate the general second-order elliptic problem in two dimensions. Some optimal numerical integration formulas are presented and analyzed. These formulas are derived on a reference quadrilateral which can be linearly mapped to a physical quadrilateral. The novelty of th...