Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

• URL: http://arxiv.org/abs/2608.04752v1
• Date: Wed, 05 Aug 2026 12:20:53 GMT
• Title: Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction
• Abstract summary: Recent splat-based tomography has demonstrated both high reconstruction quality and fast convergence in cone-beam sparse-view CT.<n>We observe distinctive streak and strip artifacts that are far more pronounced than in conventional reconstruction methods.<n>We derive a stable gradient-based framework that jointly refines geometric parameters during reconstruction.
• Score: 12.315488379543773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: X-ray computed tomography (CT) reconstructs volumetric representations of objects from projection images obtained by transmitting X-rays through a target. Recent splat-based tomography, which represents a volume as a continuous distribution of 3D Gaussians, has demonstrated both high reconstruction quality and fast convergence in cone-beam sparse-view CT. However, when deployed in real CT systems with limited and non-uniform view distributions, we observe distinctive streak and strip artifacts that are far more pronounced than in conventional reconstruction methods. Through detailed analysis, we show that these artifacts primarily originate from pose inaccuracies in the acquisition geometry rather than from view sparsity itself. We revisit pose sensitivity in the splatting formulation and derive a stable gradient-based framework that jointly refines geometric parameters during reconstruction. Our study not only identifies how pose perturbations propagate through the differentiable projection operator but also reveals why splat-based CT is particularly vulnerable to geometric misalignment. The resulting formulation remains lightweight and easily integrable into existing pipelines while substantially improving reconstruction fidelity under real-world sparse-view conditions.

Related papers

• GenRec: Knowing Where to Reconstruct and Where to Generate [106.48347271421765]
  GenRec is a flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow.<n>It attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones.
  arXiv  Detail & Related papers  (2026-08-18T14:31:19Z)
• Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction [25.938115587172945]
  Reconstructing a CT volume from only a few X-ray views is severely ill-posed.<n>We propose LiftXR, an interleaved, geometry-guided framework that explicitly incorporates spatial layout recovery into CT reconstruction.<n>LiftXR consistently outperforms recent X-ray-to-CT reconstruction methods, establishing a new state of the art.
  arXiv  Detail & Related papers  (2026-08-18T01:23:36Z)
• LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction [6.182438051513934]
  Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views.<n> angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of fine details.<n>We propose Lucid, a sparsity-adaptive, consistency-guided reconstruction framework based on a Flow Matching generative prior for sparse-view CT.
  arXiv  Detail & Related papers  (2026-06-15T04:38:30Z)
• Texture-preserving implicit neural representation for Cone beam CT truncated reconstruction [11.587045623341888]
  Cone-beam computed tomography (CBCT) frequently suffers from data truncation, which introduces severe artifacts.<n>Existing deep learning methods for truncatedCBCT reconstruction suffer from serious limitations.<n>We introduce a self-supervised 3D reconstruction framework based on neural scene representations.
  arXiv  Detail & Related papers  (2026-06-04T11:33:21Z)
• Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstruction [14.00351191217297]
  This work integrates wavelet multi-resolution analysis with 3DGS to enhance sparse reconstruction.<n>We introduce a spectrally-decoupled Gaussian representation that stratifies the volumetric field into a geometric base component and a residual detail component.<n>Experiments on clinical datasets demonstrate that RGS enables the reconstructed images to capture highly refined geometric textures.
  arXiv  Detail & Related papers  (2026-04-30T07:59:18Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction [26.60542816157164]
  Sparse-view computed tomography (CT) is critical for reducing radiation exposure to patients.<n>Recent advances in radiative 3D Gaussian Splatting have enabled fast and accurate sparse-view CT reconstruction.<n>Existing active view selection methods fail to capture the unique geometric ambiguities and physical attenuation properties inherent in Xray imaging.
  arXiv  Detail & Related papers  (2026-03-06T20:16:00Z)
• Semantic contrastive learning for orthogonal X-ray computed tomography reconstruction [2.667606911741401]
  Recent advances in deep learning-based methods have improved reconstruction quality, but challenges still remain.<n>We propose a novel semantic feature contrastive learning loss function that evaluates semantic similarity in high-level latent spaces and anatomical similarity in shallow latent spaces.
  arXiv  Detail & Related papers  (2025-12-27T18:33:37Z)
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment [48.147381011235446]
  3D Gaussian Splatting has recently emerged as an efficient solution for real-time novel view synthesis.<n>We propose a novel method that enhances the geometric representation of 3D Gaussians through view alignment.<n>Our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
  arXiv  Detail & Related papers  (2025-10-13T14:44:50Z)
• CoCPF: Coordinate-based Continuous Projection Field for Ill-Posed Inverse Problem in Imaging [78.734927709231]
  Sparse-view computed tomography (SVCT) reconstruction aims to acquire CT images based on sparsely-sampled measurements. Due to ill-posedness, implicit neural representation (INR) techniques may leave considerable holes'' (i.e., unmodeled spaces) in their fields, leading to sub-optimal results. We propose the Coordinate-based Continuous Projection Field (CoCPF), which aims to build hole-free representation fields for SVCT reconstruction.
  arXiv  Detail & Related papers  (2024-06-21T08:38:30Z)
• Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction [53.93674177236367]
  Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. We introduce a novel geometry-aware encoder-decoder framework to solve this problem.
  arXiv  Detail & Related papers  (2023-03-26T14:38:42Z)
• Orientation-Shared Convolution Representation for CT Metal Artifact Learning [63.67718355820655]
  During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts. Existing deep-learning-based methods have gained promising reconstruction performance. We propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts.
  arXiv  Detail & Related papers  (2022-12-26T13:56:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.