A5074999513- 3D Shape Modeling and Analysis
- Image Processing and 3D Reconstruction
- Human Pose and Action Recognition
- Dental Radiography and Imaging
- Digital Imaging in Medicine
- Computer Graphics and Visualization Techniques
- Face recognition and analysis
- Advanced Numerical Analysis Techniques
- Generative Adversarial Networks and Image Synthesis
- Image and Object Detection Techniques
- 3D Surveying and Cultural Heritage
- Video Surveillance and Tracking Methods
- Human Motion and Animation
Polytechnique Montréal
2021-2024
Designing a dental crown is time-consuming and labor intensive process. Our goal to simplify design minimize the tediousness of making manual adjustments while still ensuring highest level accuracy consistency. To this end, we present new end- to-end deep learning approach, coined Dental Mesh Completion (DMC), generate mesh conditioned on point cloud context. The context includes tooth prepared receive its surroundings, namely two adjacent teeth three closest in opposing jaw. We formulate...
Designing a synthetic crown is time-consuming, inconsistent, and labor-intensive process. In this work, we present fully automatic method that not only learns human design dental crowns, but also improves the consistency, functionality, esthetic of crowns. Following success in point cloud completion using transformer-based network, tackle problem generation as point-cloud around prepared tooth. To end, use geometry-aware transformer to generate Our main contribution add margin line...
During a crown generation procedure, dental technicians depend on commercial software to generate margin line define the design boundary for crown. The remains non-reproducible, inconsistent, and challenging procedure. In this work, we propose points prepared teeth meshes using adaptive point learning inspired by AdaPointTr model. We extracted ground truth lines as clouds from bottom meshes. chamfer distance (CD) infoCD loss functions were used training supervised deep model that outputs...
Automatic and accurate dental arch segmentation is a fundamental task in computer-aided dentistry. Recent trends digital dentistry are tackling the design of 3D crowns using artificial intelligence, which initially requires proper semantic teeth from intraoral scans (IOS). In practice, most IOS partial with as few three on scanned arch, some them might have preparations, missing, or incomplete teeth. Existing deep learning-based methods (e.g., MeshSegNet, DArch) were proposed for...
Designing a synthetic crown is time-consuming, inconsistent, and labor-intensive process. In this work, we present fully automatic method that not only learns human design dental crowns, but also improves the consistency, functionality, esthetic of crowns. Following success in point cloud completion using transformer-based network, tackle problem generation as point-cloud around prepared tooth. To end, use geometry-aware transformer to generate Our main contribution add margin line...