Search papers, labs, and topics across Lattice.
This paper introduces X-Splat, a novel Gaussian Splatting framework that generates 3D dental volumes from a single panoramic radiograph (PXR), addressing the challenge of underdetermined reconstruction due to the integration of 3D information into a 2D image. By leveraging the panoramic acquisition geometry and employing learnable anisotropic Gaussian primitives, X-Splat effectively constrains the generation process, resulting in anatomically consistent and sharp reconstructions of dental structures. The method demonstrates superior performance over existing NeRF- and GAN-based approaches, successfully recovering critical anatomical features such as individual teeth and the mandibular canal, which were previously difficult to reconstruct.
X-Splat achieves anatomically accurate 3D dental reconstructions from a single 2D panoramic image, outperforming traditional methods that struggle with detail retention.
Generating a 3D dental volume from a single panoramic radiograph (PXR) could provide a low-radiation alternative to Cone-Beam Computed Tomography (CBCT), but the problem is highly underdetermined: panoramic acquisition integrates 3D attenuation along curved X-ray paths into a 2D image, leaving depth-resolved anatomy unobserved. Existing implicit and generative approaches often produce oversmoothed geometry or anatomically inconsistent hallucinations, lacking geometry-driven supervision and relying on smooth representations unable to precisely localize sharp anatomical boundaries. We propose X-Splat, the first Gaussian Splatting framework for generating CBCT-like 3D dental volumes from a single PXR. X-Splat uses the known panoramic acquisition geometry as a generation scaffold: learnable anisotropic Gaussian primitives are initialized along the X-ray paths that formed the input image and adjusted in a single feed-forward pass, constrained by Beer-Lambert reprojection and multi-view radiographic training supervision. A lightweight residual refiner adds dataset-level anatomical priors without overriding the geometry already resolved by the Gaussians. We train on synthetic PXR-CBCT pairs, enabling direct volumetric supervision without paired real scans. We further introduce segmentation-based geometry-aware metrics, providing the first evaluation of PXR-based generation over maxillofacial anatomy. X-Splat outperforms NeRF- and GAN-based baselines, recovering individual teeth, cortical boundaries, and alveolar structure, including the mandibular canal which prior methods fail to reconstruct. Code will be available at https://github.com/tomek1911/X-Splat
