# ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image

arXiv: https://arxiv.org/abs/2211.15502 · HTML: https://mlsanity.com/paper/2211.15502/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 12 references that are in the map.
- First posted on arXiv 25 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph](https://mlsanity.com/paper/2108.13004/) (2021)

## Built on by (most cited first, 3 of 3)

- [ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs](https://mlsanity.com/paper/2506.13195/) (2025)
- [X2BR: High-Fidelity 3D Bone Reconstruction from a Planar X-Ray Image with Hybrid Neural Implicit Methods](https://mlsanity.com/paper/2504.08675/) (2025)
- [K-U-KAN: Koopman-Enhanced U-KAN for 3D Dental Reconstruction from a Single Panoramic X-ray Radiograph](https://mlsanity.com/paper/2605.25163/) (2026)

## Abstract (arXiv)

In orthodontic treatment, a full tooth model consisting of both the crown and root is indispensable in making the treatment plan. However, acquiring tooth root information to obtain the full tooth model from CBCT images is sometimes restricted due to the massive radiation of CBCT scanning. Thus, reconstructing the full tooth shape from the ready-to-use input, e.g., the partial intra-oral scan and the 2D panoramic image, is an applicable and valuable solution. In this paper, we propose a neural network, called ToothInpaintor, that takes as input a partial 3D dental model and a 2D panoramic image and reconstructs the full tooth model with high-quality root(s). Technically, we utilize the implicit representation for both the 3D and 2D inputs, and learn a latent space of the full tooth shapes. At test time, given an input, we successfully project it to the learned latent space via neural optimization to obtain the full tooth model conditioned on the input. To help find the robust projection, a novel adversarial learning module is exploited in our pipeline. We extensively evaluate our method on a dataset collected from real-world clinics. The evaluation, comparison, and comprehensive ablation studies demonstrate that our approach produces accurate complete tooth models robustly and outperforms the state-of-the-art methods.