# ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs

arXiv: https://arxiv.org/abs/2506.13195 · HTML: https://mlsanity.com/paper/2506.13195/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [Vision Transformer for NeRF-Based View Synthesis from a Single Input Image](https://mlsanity.com/paper/2207.05736/) (2022)
- [Implicit Neural Representation in Medical Imaging: A Comparative Survey](https://mlsanity.com/paper/2307.16142/) (2023)
- [ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration](https://mlsanity.com/paper/2104.06468/) (2021)
- [Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.06681/) (2023)
- [SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields](https://mlsanity.com/paper/2211.17048/) (2022)
- [X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph](https://mlsanity.com/paper/2108.13004/) (2021)
- [Neural Radiance Fields in Medical Imaging: A Survey](https://mlsanity.com/paper/2402.17797/) (2024)
- [3DPX: Progressive 2D-to-3D Oral Image Reconstruction with Hybrid MLP-CNN Networks](https://mlsanity.com/paper/2408.01292/) (2024)
- [PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray](https://mlsanity.com/paper/2411.03725/) (2024)
- [U-Net Training with Instance-Layer Normalization](https://mlsanity.com/paper/1908.08466/) (2019)
- [ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image](https://mlsanity.com/paper/2211.15502/) (2022)
- [Oral-3Dv2: 3D Oral Reconstruction from Panoramic X-Ray Imaging with Implicit Neural Representation](https://mlsanity.com/paper/2303.12123/) (2023)
- [NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographs](https://mlsanity.com/paper/2304.04027/) (2023)
- [NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface](https://mlsanity.com/paper/2503.07491/) (2025)
- [OralViewer: 3D Demonstration of Dental Surgeries for Patient Education with Oral Cavity Reconstruction from a 2D Panoramic X-ray](https://mlsanity.com/paper/2101.00098/) (2020)
- [Survey on Fundamental Deep Learning 3D Reconstruction Techniques](https://mlsanity.com/paper/2407.08137/) (2024)

## Built on by (most cited first, 2 of 2)

- [HyDAR-Pano3D: A Hybrid Disentangled Anatomical Recovery Framework for Panoramic-to-3D Reconstruction](https://mlsanity.com/paper/2605.20827/) (2026)
- [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)

Dental diagnosis relies on two primary imaging modalities: panoramic radiographs (PX) providing 2D oral cavity representations, and Cone-Beam Computed Tomography (CBCT) offering detailed 3D anatomical information. While PX images are cost-effective and accessible, their lack of depth information limits diagnostic accuracy. CBCT addresses this but presents drawbacks including higher costs, increased radiation exposure, and limited accessibility. Existing reconstruction models further complicate the process by requiring CBCT flattening or prior dental arch information, often unavailable clinically. We introduce ViT-NeBLa, a vision transformer-based Neural Beer-Lambert model enabling accurate 3D reconstruction directly from single PX. Our key innovations include: (1) enhancing the NeBLa framework with Vision Transformers for improved reconstruction capabilities without requiring CBCT flattening or prior dental arch information, (2) implementing a novel horseshoe-shaped point sampling strategy with non-intersecting rays that eliminates intermediate density aggregation required by existing models due to intersecting rays, reducing sampling point computations by 52 %, (3) replacing CNN-based U-Net with a hybrid ViT-CNN architecture for superior global and local feature extraction, and (4) implementing learnable hash positional encoding for better higher-dimensional representation of 3D sample points compared to existing Fourier-based dense positional encoding. Experiments demonstrate that ViT-NeBLa significantly outperforms prior state-of-the-art methods both quantitatively and qualitatively, offering a cost-effective, radiation-efficient alternative for enhanced dental diagnostics.