TAlignDiff: Automatic Tooth Alignment assisted by Diffusion-based Transformation Learning
Yunbi Liu, Enqi Tang, Shiyu Li, Hui Shuai, Lei Ma, Juncheng Li, Kuai Yu, Shu Lou
Abstract
Orthodontic treatment hinges on tooth alignment, which significantly affects occlusal function, facial aesthetics, and patients' quality of life. Current deep learning approaches often predict transformation matrices for the misaligned tooth point cloud via point-to-point geometric constraints to achieve tooth alignment, ignoring the clinically specific distributions exhibited in these matrices. To address this, we introduce a new automatic tooth alignment method named TAlignDiff, which is assisted by diffusion-based transformation learning. TAlignDiff comprises two main components: a primary point cloud-based regression network (PRN) and a diffusion-based transformation matrix denoising module (DTMD). Geometry-constrained losses supervise PRN learning for point cloud-level alignment. DTMD, as an auxiliary module, learns the latent distribution of matrices from clinical data. We integrate point cloud-based transformation regression and diffusion-based transformation modeling into a unified framework, allowing bidirectional feedback between geometric constraints and diffusion refinement. We validate our method on a challenge dataset from clinical practice and an extra orthodontic dataset. Its efficacy was confirmed through effective ablation studies and comparative analyses, highlighting its potential for application in orthodontic treatment.
BibTeX
@inproceedings{cvpr2026_taligndiffautoma,
title = {TAlignDiff: Automatic Tooth Alignment assisted by Diffusion-based Transformation Learning},
author = {Yunbi Liu and Enqi Tang and Shiyu Li and Hui Shuai and Lei Ma and Juncheng Li and Kuai Yu and Shu Lou and Yongchu Pan and Qingshan Liu},
booktitle = {CVPR 2026},
year = {2026}
}