A5007389144- 3D Shape Modeling and Analysis
- Dental Radiography and Imaging
- Human Pose and Action Recognition
- Medical Image Segmentation Techniques
- 3D Surveying and Cultural Heritage
- Dental Implant Techniques and Outcomes
- Emotion and Mood Recognition
- Advanced Vision and Imaging
- Forensic Anthropology and Bioarchaeology Studies
- Orthodontics and Dentofacial Orthopedics
- Remote Sensing and LiDAR Applications
- Computer Graphics and Visualization Techniques
- Dental Research and COVID-19
- Temporomandibular Joint Disorders
- Video Surveillance and Tracking Methods
- Hand Gesture Recognition Systems
- Engineering Technology and Methodologies
- Brain Tumor Detection and Classification
- Periodontal Regeneration and Treatments
- ECG Monitoring and Analysis
- Advanced Image Processing Techniques
- AI and Big Data Applications
- Digital Imaging in Medicine
- Structural Analysis and Optimization
- Advanced Computing and Algorithms
Shandong University
2018-2024
Shenzhen University
2023-2024
Chinese University of Hong Kong
2024
University of Hong Kong
2024
University of Jinan
2016
Automatic teeth segmentation and labeling on dental models are basic tasks in computer-aided dentistry. Many existing works can achieve promising results segmentation, but they heavily rely aligned input models, which leads to additional manual intervention. Moreover, tooth is an essential task digital dentistry for treatment planning ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , orthodontic), usually ignored these methods. In...
Abstract Micro-expression recognition is a substantive cross-study of psychology and computer science, it has wide range applications (e.g., psychological clinical diagnosis, emotional analysis, criminal investigation, etc.). However, the subtle diverse changes in facial muscles make difficult for existing methods to extract effective features, which limits improvement micro-expression accuracy. Therefore, we propose multi-scale joint feature network based on optical flow images recognition....
Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due variations anatomy, imaging protocols, limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized conjunction with International...
Automatic tooth alignment target prediction is vital in shortening the planning time of orthodontic treatments and aligner designs. Generally, quality targets greatly depends on experience ability dentists has enormous subjective factors. Therefore, many knowledge-driven methods have been proposed to help inexperienced dentists. Unfortunately, existing tend directly regress motion, which lacks clinical interpretability. Tooth anatomical landmarks play a critical role orthodontics because...
Abstract 3D scanned point cloud data of teeth is popular used in digital orthodontics. The classification and semantic labelling for each tooth a key challenging task planning dental treatment. Utilizing the priori ordered position information arrangement, we propose an effective network model this paper. relative adjacency similarity feature vectors are calculated model, combine geometric into fully connected layers training task. For anomalies, present anomalies processing method to...
Abstract Image vectorization is an important yet challenging problem, especially when the input image has rich content. In this paper, we develop a novel method for automatically vectorizing natural images with feature‐aligned quad‐dominant meshes. Inspired by quadrangulation methods in 3D geometry processing, propose new directional field optimization technique encoding color gradients, sidestepping explicit computing of salient features. We further compute anisotropic scales accommodating...
Micro-expressions are the external manifestations of human psychological activities. Therefore, micro-expression recognition has important research and application value in many fields such as public services, criminal investigations, clinical diagnosis. However, particular characteristics (e.g., short duration subtle changes) micro-expressions bring great challenges to recognition. In this paper, we explore differences direction facial muscle movement when people make different expressions...
Tooth motion generation is an essential task in digital orthodontic treatment for precise and quick dental healthcare, which aims to generate the whole intermediate tooth process given initial pathological target ideal alignments. Most prior works multi-agent planning problems usually result complex solutions. Moreover, occlusal relationship between upper lower teeth often overlooked. In this paper, we propose a collaborative diffusion model. The critical insight remodel problem as process....
The paper presents a new method for constructing self-supporting surfaces using arch beams that are designed to convert their thrust into supporting force, thereby eliminating shear stress and bending moments. Our allows the placement of on boundary or within surface partitions multiple parts. use enhances stability durability, adds aesthetic appeal, greater flexibility in design process. We develop an iterative algorithm designing selfsupporting with enables user control shape through...
Nowadays, orthodontics has become an important part of modern personal life to assist one in improving mastication and raising self-esteem. However, the quality orthodontic treatment still heavily relies on empirical evaluation experienced doctors, which lacks quantitative assessment requires patients visit clinics frequently for in-person examination. To resolve aforementioned problem, we propose a novel practical mobile device-based framework precisely measuring tooth movement treatment,...
As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while unsigned (UDF) capable of representing various surfaces. However, its inherent theoretical shortcoming, i.e., non-differentiability at zero level set, would result in sub-optimal reconstruction quality. In this paper, we propose scaled-squared (S$^{2}$DF), a novel surface representation for arbitrary types. S$^{2}$DF does not distinguish between inside and...
This paper presents PCDreamer, a novel method for point cloud completion. Traditional methods typically extract features from partial clouds to predict missing regions, but the large solution space often leads unsatisfactory results. More recent approaches have started use images as extra guidance, effectively improving performance, obtaining paired data of and is challenging in practice. To overcome these limitations, we harness relatively view-consistent multi-view diffusion priors within...
In this paper, faced with the diversity and difference of clothes, we propose a novel method combined deep belief network softmax classifier to achieve classification clothes. First all, preprocess angle scaling various styles clothes images that are collected through web crawler, then do something convert image into corresponding input format. addition, DBN is trained layer-by-layer all pixels top level hyperplane. At last, apply has been completely classify strange Compared traditional...
Artificial intelligence (AI) technology is increasingly used for digital orthodontics, but one of the challenges to automatically and accurately detect tooth landmarks axes. This partly because sophisticated geometric definitions them, due large variations among individual across different types tooth. As such, we propose a deep learning approach with labeled dataset by professional dentists landmark/axis detection on model that are crucial orthodontic treatments. Our method can extract not...
In the era of Internet Things (IoT), voice control has enhanced human–machine interaction and accuracy keyword spotting (KWS) algorithms reached 97%; however, high power consumption KWS caused by their huge computing storage requirements limited application in Artificial Intelligence (AIoT) devices. this study, features are extracted utilizing fast discrete cosine transform (FDCT) for frequency-domain transformation to shorten process calculating logarithmic spectrum cepstrum. The designed...