mlsanityData to 7 Oct 2026

CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization

arXiv 2501.13073 ↗First posted 22 Jan 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Identifying anatomical landmarks in 3D dental models is essential for orthodontic treatment, yet manual placement is labor-intensive and requires expert knowledge. While machine learning methods have been proposed for automatic landmark detection in 3D Intraoral Scans (IOS), none provide a fully end-to-end solution that avoids costly tooth segmentation. We present CHaRM (Conditioned Heatmap Regression Methodology), the first fully end-to-end deep learning approach for tooth landmark detection in 3D IOS. CHaRM integrates four components: a point cloud encoder, a decoder with a heatmap regression head, a teeth-presence classification head, and the novel CHaR module. The CHaR module leverages teeth-presence information to adapt to missing teeth, improving detection accuracy in complex dental cases. Unlike two-stage workflows that segment teeth before landmarking, CHaRM operates directly on IOS point clouds, reducing complexity, avoiding error propagation, and lowering computational cost. We evaluated CHaRM with five point cloud learning backbones on IOSLandmarks-1k, a new dataset of 1,214 annotated 3D dental models. Both the dataset and code will be publicly released to address the scarcity of open data in orthodontics and foster reproducible research. CHaRM with PointMLP, named CHaRNet, achieved the best accuracy and efficiency. Compared to state-of-the-art methods (TSMDL and ALIIOS), CHaRNet reduced mean Euclidean distance error to 0.56 mm on standard dental models and 1.12 mm across all dentition type, while delivering up to 14.8x faster inference on GPU. This end-to-end approach streamlines orthodontic workflows, enhances the precision of 3D IOS analysis, and enables efficient computer-assisted treatment planning.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

33 of 62 references.

References · 33

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2020Point Transformercited by 1,462
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  10. 2020PCT: Point cloud transformercited by 730
  11. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
21 more
  1. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  2. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  3. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  4. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  5. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  6. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  7. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  8. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2018Model Evaluation, Model Selection, and Algorithm Selection in Machine Learningcited by 157
  11. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  12. 2020TransPose: Keypoint Localization via Transformercited by 126
  13. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  14. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  15. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  16. 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
  17. 2024nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Modelcited by 45
  18. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  19. 2021Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scanscited by 23
  20. 2022Teeth3DS+: An Extended Benchmark for Intraoral 3D Scans Analysiscited by 11
  21. 2021Dense Representative Tooth Landmark/axis Detection Network on 3D Modelcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Alignerscited by 0