Organizations: University of Central Florida · The Hong Kong University of Science and Technology (Guangzhou) · Tampere University · Ellis Institute Finland
Sparse-view cone-beam computed tomography (CBCT) is severely under-constrained by limited X-ray projections. Learned reconstruction can provide complementary anatomical information, but using it as a prior in patient-specific Gaussian reconstruction introduces two challenges. First, the discrepancy between the learned prior and current reconstruction is spatially non-uniform: some local differences contain useful missing 3D information, whereas others reflect prior bias. Second, even a volumetrically beneficial correction can conflict with the observed X-ray measurements. Since X-ray measurements are line integrals, spatially separated corrections may affect overlapping rays, with their signed projection responses reinforcing or partially canceling in the measurement residual, so their feasibility cannot always be assessed independently. In this paper, we introduce RePrior, a multi-stage progressive prior-correction framework that addresses correction actionability, measurement feasibility, and representation expressivity. Selective Correction Proposal (SCP) first identifies actionable signed local corrections from prior--reconstruction discrepancies. Measurement-Constrained Reconciliation (MCR) then jointly enforces their consistency with patient-specific X-ray measurements, while Hybrid Residual Enhancement (HRE) recovers additional correction capacity through complementary voxel- and Gaussian-domain degrees of freedom around the reconciled anchor. RePrior requires neither test-time ground truth nor case-specific network fine-tuning. RePrior gains approximately 2.6~dB in 3D PSNR over R2-Gaussian across LUNA16, PANORAMA, and PENGWIN. Beyond prior-assisted reconstruction, it delivers additional gains in volumetric quality and observed-view projection fidelity, with consistent gains in held-out-view fidelity in the backbone-matched evaluation.
Figures & tables
Figure 1: We introduce RePrior , a multi-stage progressive prior-correction framework which transfers learned priors into patient-specific sparse-view CBCT reconstruction through selective correction proposal, measurement-constrained reconciliation, and hybrid residual enhancement.
Figure 2: Challenges in prior-guided correction. Left: local prior differences contain both useful 3D corrections and prior bias. Right: some volumetrically beneficial corrections still conflict with X-ray measurements.
Figure 3: Overview of RePrior. (a) Learned prior VP and prior-assisted reconstruction VR . (b) SCP predicts a signed correction DA . (c) MCR jointly reconciles structured correction modes using their X-ray responses H , producing DB and the feasible anchor VB . (d) HRE combines voxel- and Gaussian-domain residual freedom under measurement guards to obtain V∗ .
Figure 4: Ray-coupled correction responses on a representative case, illustrating measurement conflict and signed compensation.
LUNA16 (90)
PANORAMA (90)
PENGWIN (50)
Method
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
SAX-NeRF (CVPR’24)
29.41
0.8311
27.57
0.8358
30.86
0.8726
X-Gaussian (ECCV’24)
19.55
0.3030
19.24
0.3546
20.41
0.3468
R 2 -GS (NeurIPS’24)
29.12
0.8357
28.42
0.8534
30.29
0.8817
Exact-GS (CVPR’26)
26.71
0.7598
26.51
0.7711
28.46
0.8134
DeepSparse-10 (TMI’26)
30.74
0.8660
26.35
0.8386
27.12
0.8461
Table 1: Main comparison on sparse-view CBCT reconstruction. Best and second-best results are shown in bold and underlined, respectively.
Figure 5: Qualitative comparison on representative LUNA16, PANORAMA, and PENGWIN cases. Red and cyan boxes mark the highlighted local regions.
Backbone
Cases
Method
3D PSNR ↑
3D SSIM ↑
2D PSNR ↑
2D SSIM ↑
R 2 -GS
90
R 2 -GS
29.12
0.8357
43.17
0.9864
90
Prior-R 2 -GS
32.09
0.8826
44.09
0.9906
90
RePrior
32.58
0.8881
44.24
0.9910
Exact-GS
30
Exact-GS
27.25
0.7749
40.60
0.9754
30
Prior-Exact-GS
31.27
0.8688
44.22
0.9893
30
RePrior
31.87
0.8754
44.35
0.9898
Table 2: Generalization across Gaussian reconstruction backbones on LUNA16.
Configuration
3D PSNR ↑
3D SSIM ↑
2D PSNR ↑
2D SSIM ↑
Prior-R 2 -GS
32.03
0.8966
46.46
0.9956
+ SCP
32.58
0.9033
46.30
0.9952
+ MCR
32.24
0.8989
46.63
0.9957
+ HRE (Full)
32.43
0.9012
47.10
0.9956
Table 3: Stage-wise ablation of RePrior.
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Feature family
Dim.
Main quantities
Multi-scale frequency
18
Five band-energy ratios, spectral centroid, high/low ratio, mid/total ratio, and total energy for VP and VR
Differential morphology
38
Gradient magnitude, surface normal, Hessian eigenstructure, structure-tensor descriptors, local variance, contrast, Laplacian, and boundary distance
Local attenuation
2
Local attenuation values of VP and VR
Direct disagreement
5
Absolute and relative attenuation discrepancy, gradient difference, normal disagreement, and local NCC
Discrepancy spectrum
7
Five discrepancy-band ratios, spectral centroid, and total discrepancy energy
Structural-anchor relation
5
Structural-feature distance and frozen AGREE/DISAGREE/P1-ONLY/P2-ONLY indicators
Appendix
Table 4: Composition of the 75 -dimensional SCP discrepancy descriptor. All features are available at test time; ground truth is used only to build the training targets in Eqs. ( 21 ) and ( 22 ).
Quantity
Constraint
Position
∥Δxi∥2≤0.2 normalized scene units
Attenuation / density
log(ρi/ρiref)≤0.1
Per-axis scale
log(si,a/si,aref)≤0.1
Physical scale
0.001≤si,a≤1
Rotation
geodesic change ≤10∘
Topology
fixed; no densification or pruning
Appendix
Table 5: Gaussian trust bounds used by HRE.
Figure S1: Additional qualitative results on LUNA16 (Part I). Each row shows an additional representative slice, while columns compare SAX-NeRF, X-Gaussian, R 2 -GS, Exact-GS, DeepSparse-10, DeepSparse-25, RePrior, and GT.
Figure S2: Additional qualitative results on LUNA16 (Part II). Additional slices and viewing planes using the same method ordering as in Fig. S1 .
Figure S3: Additional qualitative results on PANORAMA (Part I). Each row shows an additional representative slice, while columns compare SAX-NeRF, X-Gaussian, R 2 -GS, Exact-GS, DeepSparse-10, DeepSparse-25, RePrior, and GT.
Figure S4: Additional qualitative results on PANORAMA (Part II). Additional slices and viewing planes using the same method ordering as in Fig. S3 .
Figure S5: Additional qualitative results on PENGWIN (Part I). Each row shows an additional representative slice, while columns compare SAX-NeRF, X-Gaussian, R 2 -GS, Exact-GS, DeepSparse-10, DeepSparse-25, RePrior, and GT.
Figure S6: Additional qualitative results on PENGWIN (Part II). Additional slices and viewing planes using the same method ordering as in Fig. S5 .
Sparse-view Cone-Beam Computed Tomography (CBCT) reconstruction is essential for reducing radiation dose and scan effort, but remains underconstrained due to limited projection information. Recent 3D Gaussian Splatting (3DGS)-based CBCT reconstruction methods rely on gradient-driven densification, which becomes unstable under sparse acquisition and often leads to over-smoothed structures. We propose AD-GS, an Anatomical Density-guided 3D Gaussian Splatting framework that formulates Gaussian densification as an attenuation-aware Markov Chain Monte Carlo (MCMC) sampling process. By interpreting Gaussians as samples from an underlying anatomical attenuation distribution, AD-GS adaptively concentrates representation capacity in high-attenuation regions, enabling sharper structural boundaries under sparse projections. To further constrain reconstruction, we incorporate a semantic regularization based on zero-shot features from Segment Anything in Medical Images, enforcing multi-view consistency through semantic priors. Experiments on the ToothFairy3 dental CBCT dataset demonstrate that AD-GS achieves superior structural fidelity and boundary preservation compared with existing 3DGS-based approaches under sparse-view settings within the dental and maxillofacial setting. Code is available at https://github.com/yulinjiaxue/AD-GS-BMVC2026.
Zonglin Li, Kexian Xie, Feiran Li +5
Beijing University of Posts and Telecommunications · Department of Stomatology, Peking University Third Hospital · Independent Researcher +2
A long-term goal in CT imaging is to achieve fast and accurate 3D reconstruction from sparse-view projections, thereby reducing radiation exposure, lowering system cost, and enabling timely imaging in clinical workflows. Recent feed-forward approaches have shown strong potential toward this overarching goal, yet their results still suffer from artifacts and loss of fine details. In this work, we introduce Iterative Latent Volumes (ILV), a feed-forward framework that integrates data-driven priors with classical iterative reconstruction principles to overcome key limitations of prior feed-forward models in sparse-view CBCT reconstruction. At its core, ILV constructs an explicit 3D latent volume that is repeatedly updated by conditioning on multi-view X-ray features and the learned anatomical prior, enabling the recovery of fine structural details beyond the reach of prior feed-forward models. In addition, we develop and incorporate several key architectural components, including an X-ray feature volume, group cross-attention, efficient self-attention, and view-wise feature aggregation, that efficiently realize its core latent volume refinement concept. Extensive experiments on a large-scale dataset of approximately 14,000 CT volumes demonstrate that ILV significantly outperforms existing feed-forward and optimization-based methods in both reconstruction quality and speed. These results show that ILV enables fast and accurate sparse-view CBCT reconstruction suitable for clinical use. The project page is available at: https://sngryonglee.github.io/ILV/.
Four-dimensional cone-beam computed tomography (4D CBCT) provides phase-resolved volumetric images for image-guided radiotherapy. Yet good reconstruction quality usually needs many projections. This increases scan time and radiation dose. We propose STCNet, a sparse-view 4D CBCT reconstruction framework that uses spatial-temporal consistency learning. STCNet reconstructs high-quality images from only 16 projections in each respiratory phase. STCNet integrates physics-driven positional encoding to enforce geometric consistency in the projection domain and introduces temporal encoding in latent space to capture respiratory motion dynamics across phases to capture dynamic respiratory motion across phases. A dual-domain collaborative strategy jointly optimizes both projection and image domains, enhancing structural fidelity and temporal coherence. We tested STCNet on the TCIA-LUNG dataset and a CIRS thorax phantom dataset. STCNet performed better than conventional methods and recent deep learning baselines in image quality, artifact reduction, and structural preservation. On TCIA-LUNG, STCNet reached PSNR values of 33.311, 32.695, and 32.658 dB at phases 2, 5, and 8. The corresponding SSIM values were 0.845, 0.823, and 0.825. On CIRS, STCNet achieved PSNR values up to 36.497 dB and SSIM values up to 0.877. These results support STCNet as a promising framework for low-dose, phase-resolved 4D CBCT reconstruction in image-guided radiotherapy.