SparseTokenGS is a Gaussian-based, feed-forward method for sparse-view cone-beam CT reconstruction that uses a reusable token pool to maintain scan-wide context during decoding. Anchor Token Fusion and Point-Token Attention query this shared pool at anchors and query coordinates, preserving local Gaussian priors while enabling reconstruction in a single forward pass without per-scan optimization. Experiments on chest, dental, volcanic rock, and chicken datasets show that SparseTokenGS achieves superior reconstruction quality, achieving 29.51 dB PSNR and 0.842 SSIM from only six dental projections and maintaining separable tooth-and-pulp structures for root‑canal localization.
Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts....
The paper presents a three‑stage framework to extend the field of view in dental cone‑beam CT scans that are limited by truncated detector configurations. First, an implicit neural representation estimates missing projection data; second, an iterative reconstruction generates a secondary volumetric image with better anatomical consistency; third, a fast diffusion model refines the image for enhanced quality. Experiments show reduced truncation artifacts and improved reconstruction of structures beyond the original field of view.
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.
Dental cone-beam computed tomography (CBCT) systems often employ detector configurations that provide a truncated field of view (FOV) that only captures a small part of the patient's anatomy. In this...
Sparse-view computed tomography is a severely ill-posed inverse problem, where recent 3D Gaussian Splatting methods offer an efficient explicit representation for tomographic reconstruction. However, we find that projection-domain optimization can be misleading in this setting: the rendered projections may continue to improve while the reconstructed volume deteriorates.
arXiv:2609.37605v1 Announce Type: cross Abstract: Supervised deep learning has advanced sparse-view tomographic reconstruction. However, conventional models, which typically map filtered back-project...
The paper introduces a method for extremely sparse‑view computed tomography (xSV‑CT) that learns a pose‑aware diffusion prior from a single 2D projection per training sample. During inference, the diffusion process is guided by measured‑view fidelity, shared‑volume reprojection, and projection‑physics consistency to reconstruct 3D volumes from only 1, 4, or 8 views. Experiments on two public CT datasets show that this approach outperforms or matches baselines that rely on dense‑volume supervision, achieving superior novel‑view synthesis and competitive reconstruction quality.
arXiv:2606. 16212v1 Announce Type: cross Abstract: Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views, but angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of fine details.
arXiv:2608. 15246v1 Announce Type: cross Abstract: Sparse-view computed tomography (CT) reduces radiation dose by acquiring fewer projection views, but the resulting inverse problem is highly ill-posed and often produces severe streak artifacts.
The paper introduces $K$-NeAS, a scalable neural architecture for multi-material CT reconstruction that replaces separate material networks with a shared latent backbone and a differentiable $K$-material soft selector. It automates attenuation bounds using a Gaussian Mixture Model and adds a scheduled auxiliary floater loss to reduce geometric hallucinations in sparse-view settings. Evaluated on four clinical CBCT datasets, $K$-NeAS achieves higher 3D volumetric fidelity—up to a 1.88 dB PSNR gain over a single-material baseline—and shows improved robustness under extreme sparsity, outperforming baselines by up to 1.17 dB.
arXiv:2609.10376v1 Announce Type: new Abstract: Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is...
EUReCA is a geometry‑aware, feed‑forward model that reconstructs cone‑beam CT images from 8–100 projections without needing view‑specific retraining. It encodes each projection with a shared multiscale backbone, back‑projects features into 3‑D grids, aggregates variable views at fixed cost, and refines the volume using a global transformer and decoder. On simulated and real patient data, EUReCA outperforms existing feed‑forward and iterative methods, achieving high PSNR and superior performance across all tested view counts.