A dynamic arrangement framework for automatic tooth alignment based on orthodontic rules

Automatically achieving functionally and aesthetically aligned teeth is a critical task in computer-aided orthodontic treatment. However, existing expert rule-based approaches still require manual intervention and focus solely on occlusion functionality. Meanwhile, data-driven methods rely on large paired datasets of pre- and post-treatment cases, making it challenging to address issues such as missing teeth or collisions effectively. To alleviate these problems, this paper proposes a novel framework DyOrthoAlign that translates the automatic tooth alignment into a dynamic arrangement process based on orthodontic rules. Our DyOrthoAlign consists of two stages. We first construct the ideal dental occlusion curve based on tooth anatomical features. Then, we arrange each tooth along the ideal occlusion curve in a specific order and a series of decisions. The dynamic arrangement process continues until all the teeth are arranged, resulting in the final ideal tooth arrangement. Extensive qualitative and quantitative experiments validate our framework can produce ideal tooth alignment and offer significant practical value for personalized and efficient orthodontic treatment.