Xuequan Lu

Xuequan Lu
Deakin University · School of Information Technology

PhD

About

97
Publications
11,163
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
599
Citations
Introduction
My research interests mainly fall into the category of Visual Data Computing, for example, geometry modeling, processing and analysis, animation/simulation, 2D data processing and analysis. More information including latest news, results and codes can be found at: http://www.xuequanlu.com.

Publications

Publications (97)
Preprint
In-place gesture-based virtual locomotion techniques enable users to control their viewpoint and intuitively move in the 3D virtual environment. A key research problem is to accurately and quickly recognize in-place gestures, since they can trigger specific movements of virtual viewpoints and enhance user experience. However, to achieve real-time e...
Article
Most existing 3D geometry copy detection research focused on 3D watermarking, which first embeds “watermarks” and then detects the added watermarks. However, this kind of methods is non-straightforward and may be less robust to attacks such as cropping and noise. In this paper, we focus on a fundamental and practical research problem: judging wheth...
Preprint
Point cloud filtering and normal estimation are two fundamental research problems in the 3D field. Existing methods usually perform normal estimation and filtering separately and often show sensitivity to noise and/or inability to preserve sharp geometric features such as corners and edges. In this paper, we propose a novel deep learning method to...
Preprint
Full-text available
Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised learning based upon masking local surface patches for 3D point cloud data has been under-explored. In this paper, we propose masked Au...
Article
Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction confidence to filter low-confidence pseudo labels, thus remaining high-confidence errors and wasting many low-...
Article
Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model. Besides, the local regional consistency in UDA has been...
Article
Full-text available
Nematodes are ubiquitous in soil representing different trophic levels and occupying a central position in the detritus food web. Nematodes have been widely used for biomonitoring of soil quality and health. However, their application in bio-indicator is limited due to the taxonomic identification is laborious, and largely relying on morphological...
Article
Full-text available
We propose a robust, anisotropic normal estimation method for both point clouds and meshes using a low rank matrix approximation algorithm. First, we compute a local feature descriptor for each point and find similar, non-local neighbors that we organize into a matrix. We then show that a low rank matrix approximation algorithm can robustly estimat...
Article
Full-text available
Color transfer, which plays a key role in image editing, has attracted noticeable attention recently. It has remained a challenge to date due to various issues such as time-consuming manual adjustments and prior segmentation issues. In this paper, we propose to model color transfer under a probability framework and cast it as a parameter estimation...
Preprint
Full-text available
Histopathological image analysis is the gold standard to diagnose cancer. Carcinoma is a subtype of cancer that constitutes more than 80% of all cancer cases. Squamous cell carcinoma and adenocarcinoma are two major subtypes of carcinoma, diagnosed by microscopic study of biopsy slides. However, manual microscopic evaluation is a subjective and tim...
Article
Histopathological image analysis is the gold standard to diagnose cancer. Carcinoma is a subtype of cancer that constitutes more than 80% of all cancer cases. Squamous cell carcinoma and adenocarcinoma are two major subtypes of carcinoma, diagnosed by microscopic study of biopsy slides. However, manual microscopic evaluation is a subjective and tim...
Preprint
Full-text available
As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use. Existing point cloud filtering methods either cannot preserve sharp features or result in uneven point distribution in the filtered output. To address this problem, this paper introduces a point cloud filtering method that considers both point...
Preprint
Full-text available
Intracranial aneurysms are common nowadays and how to detect them intelligently is of great significance in digital health. While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data. In particular, our method...
Article
Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce the domain shifts in pixel level, feature level, and output level. However, almost all of them largely neglect the contextual dependency, which is generally shared a...
Article
Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not requir...
Preprint
Normal estimation on 3D point clouds is a fundamental problem in 3D vision and graphics. Current methods often show limited accuracy in predicting normals at sharp features (e.g., edges and corners) and less robustness to noise. In this paper, we propose a novel normal estimation method for point clouds. It consists of two phases: (a) feature encod...
Preprint
Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not requir...
Preprint
(see PDF here: https://arxiv.org/abs/2110.06632) Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less attention to date. In this paper, we propose a simple yet effective...
Preprint
Full-text available
Unsupervised domain adaptation (UDA) aims to bridge the domain shift between the labeled source domain and the unlabeled target domain. However, most existing works perform the global-level feature alignment for semantic segmentation, while the local consistency between the regions has been largely neglected, and these methods are less robust to ch...
Preprint
3D anatomical landmarks play an important role in health research. Their automated prediction/localization thus becomes a vital task. In this paper, we introduce a deformation method for 3D anatomical landmarks prediction. It utilizes a source model with anatomical landmarks which are annotated by clinicians, and deforms this model non-rigidly to m...
Preprint
Most existing 3D geometry copy detection research focused on 3D watermarking, which first embeds ``watermarks'' and then detects the added watermarks. However, this kind of methods is non-straightforward and may be less robust to attacks such as cropping and noise. In this paper, we focus on a fundamental and practical research problem: judging whe...
Conference Paper
Full-text available
Internet of Things (IoT) based applications face an increasing number of potential security risks, which need to be systematically assessed and addressed. Expert-based manual assessment of IoT security is a predominant approach, which is usually inefficient. To address this problem, we propose an automated security assessment framework for IoT netw...
Preprint
Full-text available
Internet of Things (IoT) based applications face an increasing number of potential security risks, which need to be systematically assessed and addressed. Expert-based manual assessment of IoT security is a predominant approach, which is usually inefficient. To address this problem, we propose an automated security assessment framework for IoT netw...
Article
Existing research works in scene image classification have focused on different aspects such as content features (e.g., visual information), context features (e.g., annotations, semantic information, etc.) and both. However, such works suffer from various issues such as higher feature size and lower classification performance. In this paper, we pro...
Preprint
[Download link: https://arxiv.org/abs/2108.11082. Please cite it if possible, Thanks] Face recognition is one of the most studied research topics in the community. In recent years, the research on face recognition has shifted to using 3D facial surfaces, as more discriminating features can be represented by the 3D geometric information. This surve...
Preprint
Walking in place for moving through virtual environments has attracted noticeable attention recently. Recent attempts focused on training a classifier to recognize certain patterns of gestures (e.g., standing, walking, etc) with the use of neural networks like CNN or LSTM. Nevertheless, they often consider very few types of gestures and/or induce l...
Preprint
Full-text available
Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination or weather, while distinct camera intrinsic parameters appear commonly in different domains, and their influe...
Preprint
Full-text available
Domain adaptation aims to bridge the domain shifts between the source and target domains. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge on a specific dimension, thus leading to less desired adaptation performance. In this paper, we study a practical...
Preprint
Full-text available
Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Although the domain shifts may exist in various dimensions such as appearance, textures, etc, the contextual dependency, which is generally shared across different domains, is neglected by recent methods. In this paper, we utilize...
Article
Facial action unit (AU) detection in the wild is a challenging problem, due to the unconstrained variability in facial appearances and the lack of accurate annotations. Most existing methods depend on either impractical labor-intensive labeling or inaccurate pseudo labels. In this paper, we propose an end-to-end unconstrained facial AU detection fr...
Article
It is significant to achieve automatic arrangement for bas-relief layout which can be noticeably more efficient than the time-consuming manual process. In fact, nearly none work has been reported in terms of bas-relief layout arrangement. In this paper, we propose a novel approach to tackle this problem. Specifically, we first identify the evaluati...
Preprint
Full-text available
The free-form deformation model can represent a wide range of non-rigid deformations by manipulating a control point lattice over the image. However, due to a large number of parameters, it is challenging to fit the free-form deformation model directly to the deformed image for deformation estimation because of the complexity of the fitness landsca...
Article
Previous methods for representing scene images based on deep learning primarily consider either the foreground or background information as the discriminating clues for the classification task. However, scene images also require additional information (hybrid) to cope with the inter-class similarity and intra-class variation problems. In this paper...
Article
Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive. In this paper, we propose a self-supervised clustering framework for grouping plant disease images based on the vulnerability of Kernel K-means. The main idea is to establish a cross i...
Article
Full-text available
Impressive progress has been recently witnessed on deep unsupervised clustering and feature disentanglement. In this paper, we propose a novel method on top of one recent architecture with a novel explanation of Gaussian mixture model (GMM) membership, accompanied by a GMM loss to enhance the clustering. The GMM loss is optimized with the explicitl...
Preprint
Full-text available
Face deepfake detection has seen impressive results recently. Nearly all existing deep learning techniques for face deepfake detection are fully supervised and require labels during training. In this paper, we design a novel deepfake detection method via unsupervised contrastive learning. We first generate two different transformed versions of an i...
Article
Facial expression transfer between two unpaired images is a challenging problem, as fine-grained expression is typically tangled with other facial attributes. Most existing methods treat expression transfer as an application of expression manipulation, and use predicted global expression, landmarks or action units (AUs) as a guidance. However, the...
Preprint
Full-text available
Nematode worms are one of most abundant metazoan groups on the earth, occupying diverse ecological niches. Accurate recognition or identification of nematodes are of great importance for pest control, soil ecology, bio-geography, habitat conservation and against climate changes. Computer vision and image processing have witnessed a few successes in...
Preprint
[PDF available at: https://arxiv.org/abs/2101.06820] Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive. In this paper, we propose a self-supervised clustering framework for grouping plant disease images based on the vulnerability of Ke...
Article
Full-text available
Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acquired in low-light situations: (1) a blurred image t...
Article
Full-text available
In this paper, we make two contributions. The first is to propose a new keyframe extraction algorithm, which reduces the keyframe redundancy and reduces the motion sequence reconstruction error. Secondly, a new motion sequence reconstruction method is proposed, which further reduces the error of motion sequence reconstruction. Specifically, we trea...
Article
Full-text available
Abstract Evolutionary algorithms (EAs) and swarm algorithms (SAs) have shown their usefulness in solving combinatorial and NP-hard optimization problems in various research fields. However, in the field of computer vision, related surveys have not been updated during the last decade. In this study, inspired by the recent development of deep neural...
Conference Paper
Nowadays it is prevalent to take features extracted from pre-trained deep learning models as image representations which have achieved promising classification performance. Existing methods usually consider either object-based features or scene-based features only. However, both types of features are important for complex images like scene images,...
Article
Full-text available
Federated Learning (FL) is an emerging research field that yields a global trained model from different local clients without violating data privacy. Existing FL techniques often ignore the effective distinction between local models and the aggregated global model when doing the client-side weight update, as well as the distinction of local models...
Conference Paper
Full-text available
Keyframes extraction, a fundamental problem in video processing and analysis, has remained a challenge to date. In this paper, we introduce a novel method to effectively extract keyframes of a video. It consists of four steps. At first, we generate initial clips for the classified frames, based on consistent content within a clip. Using empirical e...
Conference Paper
Full-text available
It has become increasingly challenging to distinguish real faces from their visually realistic fake counterparts, due to the great advances of deep learning based face manipulation techniques in recent years. In this paper, we introduce a deep learning method to detect face manipulation. It consists of two stages: feature extraction and binary clas...
Conference Paper
Full-text available
3D human segmentation has seen noticeable progress in recent years. It, however, still remains a challenge to date. In this paper, we introduce a deep patch-based method for 3D human segmentation. We first extract a local surface patch for each vertex and then parameterize it into a 2D grid (or image). We then embed identified shape descriptors int...
Article
Full-text available
Point cloud filtering is a fundamental problem in geometry modeling and processing. Despite of significant advancement in recent years, the existing methods still suffer from two issues: 1) they are either designed without preserving sharp features or less robust in feature preservation; and 2) they usually have many parameters and require tedious...
Article
Full-text available
In evolutionary algorithms, genetic operators iteratively generate new offspring which constitute a potentially valuable set of search history. To boost the performance of offspring generation in the real-coded genetic algorithm (RCGA), in this paper, we propose to exploit the search history cached so far in an online style during the iteration. Sp...
Article
The goal of zero-shot learning (ZSL) is to build a classifier that recognizes novel categories with no corresponding annotated training data. The typical routine is to transfer knowledge from seen classes to unseen ones by learning a visual-semantic embedding. Existing multi-label zero-shot learning approaches either ignore correlations among label...
Preprint
It has become increasingly challenging to distinguish real faces from their visually realistic fake counterparts, due to the great advances of deep learning based face manipulation techniques in recent years. In this paper, we introduce a deep learning method to detect face manipulation. It consists of two stages: feature extraction and binary clas...
Article
Full-text available
Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blur (e.g., motion blur, out-of-focus and space-variant) remarkably increase challenges for keypoint de...
Preprint
[see PDF at: https://arxiv.org/abs/2008.13626] Color transfer, which plays a key role in image editing, has attracted noticeable attention recently. It has remained a challenge to date due to various issues such as time-consuming manual adjustments and prior segmentation issues. In this paper, we propose to model color transfer under a probability...
Preprint
Full-text available
Feature-preserving mesh denoising has received noticeable attention recently. Many methods often design great weighting for anisotropic surfaces and small weighting for isotropic surfaces, to preserve sharp features. However, they often disregard the fact that small weights still pose negative impacts to the denoising outcomes. Furthermore, it may...
Preprint
3D human segmentation has seen noticeable progress in re-cent years. It, however, still remains a challenge to date. In this paper, weintroduce a deep patch-based method for 3D human segmentation. Wefirst extract a local surface patch for each vertex and then parameterizeit into a 2D grid (or image). We then embed identified shape descriptorsinto t...
Preprint
[See PDF at: https://arxiv.org/abs/2006.03217] Existing research in scene image classification has focused on either content features (e.g., visual information) or context features (e.g., annotations). As they capture different information about images which can be complementary and useful to discriminate images of different classes, we suppose th...
Preprint
[See PDF at: https://arxiv.org/abs/2006.03199] Previous methods for representing scene images based on deep learning primarily consider either the foreground or background information as the discriminating clues for the classification task. However, scene images also require additional information (hybrid) to cope with the inter-class similarity a...
Preprint
Full-text available
[See PDF at: https://arxiv.org/abs/2005.10999] Face spoofing causes severe security threats in face recognition systems. Previous anti-spoofing works focused on supervised techniques, typically with either binary or auxiliary supervision. Most of them suffer from limited robustness and generalization, especially in the cross-dataset setting. In th...
Article
Full-text available
A large number of geometric representations have been proposed to address the needs of specific engineering applications. This, in turn, exacerbates the inherent challenges associated with system interoperability for downstream engineering applications. In this paper, we define the Maximal Disjoint Ball Decomposition (MDBD) as the location of the l...
Preprint
Point cloud filtering, the main bottleneck of which is removing noise (outliers) while preserving geometric features, is a fundamental problem in 3D field. The two-step schemes involving normal estimation and position update have been shown to produce promising results. Nevertheless, the current normal estimation methods including optimization ones...