Authors : Su Yang, Jiyong Han, Sang-Heon Lim, Ji-Yong Yoo, SuJeong Kim, Dahyun Song, Sunjung Kim, Jun-Min Kim, and Won-Jin Yi,
Journal : Scientific Reports
Related Product : Single-Pro
Date Published : 03 October 2024
Download
Abstract. Dental prosthesis is important in designing artificial replace ments to restore the function and appearance of teeth. However, design ing a patient-specific dental prosthesis is still labor-intensive and depends on dental professionals with knowledge of oral anatomy and their expe rience. Also, the initial tooth template for designing dental crowns is not personalized. In this paper, we propose a novel point-to-mesh gen eration transformer (DCrownFormer) to directly and efficiently generate dental crown meshes from point inputs of 3D scans of antagonist and preparation teeth. Specifically, to learn morphological relationships be tween a point input and generated points of a dental crown, we introduce a morphology-aware cross-attention module (MCAM) in a transformer decoder and curvature-penalty loss (CPL). Furthermore, we adopt Dif ferentiable Poisson surface reconstruction for mesh reconstruction from generated points and normals of a dental crown by directly optimizing an indicator function using mesh reconstruction loss (MRL). Experimental results demonstrate the superiority of DCrwonFormer compared with other methods, by improving morphological details of occlusal surfaces such as dental grooves and cusps. We further validate the effectiveness of MCAM,MRL,andsignificant benefits of CPL through ablation studies. The code is available at https://github.com/suyang93/DCrownFormer/.
Authors : Su Yang, Jiyong Han, Sang-Heon Lim, Ji-Yong Yoo, SuJeong Kim, Dahyun Song, Sunjung Kim, Jun-Min Kim, and Won-Jin Yi,
Journal : Scientific Reports
Related Product : Single-Pro
Date Published : 03 October 2024
Download
Abstract. Dental prosthesis is important in designing artificial replace ments to restore the function and appearance of teeth. However, design ing a patient-specific dental prosthesis is still labor-intensive and depends on dental professionals with knowledge of oral anatomy and their expe rience. Also, the initial tooth template for designing dental crowns is not personalized. In this paper, we propose a novel point-to-mesh gen eration transformer (DCrownFormer) to directly and efficiently generate dental crown meshes from point inputs of 3D scans of antagonist and preparation teeth. Specifically, to learn morphological relationships be tween a point input and generated points of a dental crown, we introduce a morphology-aware cross-attention module (MCAM) in a transformer decoder and curvature-penalty loss (CPL). Furthermore, we adopt Dif ferentiable Poisson surface reconstruction for mesh reconstruction from generated points and normals of a dental crown by directly optimizing an indicator function using mesh reconstruction loss (MRL). Experimental results demonstrate the superiority of DCrwonFormer compared with other methods, by improving morphological details of occlusal surfaces such as dental grooves and cusps. We further validate the effectiveness of MCAM,MRL,andsignificant benefits of CPL through ablation studies. The code is available at https://github.com/suyang93/DCrownFormer/.