SplineSplat: 3D Ray Tracing for Higher-Quality Tomography

• URL: http://arxiv.org/abs/2511.11078v1
• Date: Fri, 14 Nov 2025 08:51:42 GMT
• Title: SplineSplat: 3D Ray Tracing for Higher-Quality Tomography
• Authors: Youssef Haouchat, Sepand Kashani, Aleix Boquet-Pujadas, Philippe Thévenaz, Michael Unser,
• Abstract summary: We propose a ray-tracing algorithm that computes 3D line integrals with arbitrary projection geometries.<n>One of the components of our algorithm is a neural network that computes the contribution of the basis functions efficiently.
• Score: 12.686261071247879
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a method to efficiently compute tomographic projections of a 3D volume represented by a linear combination of shifted B-splines. To do so, we propose a ray-tracing algorithm that computes 3D line integrals with arbitrary projection geometries. One of the components of our algorithm is a neural network that computes the contribution of the basis functions efficiently. In our experiments, we consider well-posed cases where the data are sufficient for accurate reconstruction without the need for regularization. We achieve higher reconstruction quality than traditional voxel-based methods.

Related papers

• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering [10.560500427919647]
  We propose UniGS, a unified map representation and differentiable attribute reconstruction based on 3D Splatting.<n>Our framework integrates a multimodal viewer capable of rendering photo-realistic RGB images, geometrically accurate depth maps, consistent surface normals, and semantic logits simultaneously.
  arXiv  Detail & Related papers  (2025-10-14T06:07:57Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• Novel 3D Binary Indexed Tree for Volume Computation of 3D Reconstructed Models from Volumetric Data [0.0]
  We developed an algorithm for efficient computation of intrinsic volume of any data recovered from computed tomography (CT) or magnetic resonance (MR)<n>Our algorithm processes the data in scan-line order simultaneously with reconstruction algorithm to create a Fenwick tree, ensuring query time much faster and assisting users' edition of slicing or transforming model.
  arXiv  Detail & Related papers  (2024-12-11T11:29:53Z)
• R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
  3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction. This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
  arXiv  Detail & Related papers  (2024-05-31T08:39:02Z)
• N-BVH: Neural ray queries with bounding volume hierarchies [51.430495562430565]
  In 3D computer graphics, the bulk of a scene's memory usage is due to polygons and textures. We devise N-BVH, a neural compression architecture designed to answer arbitrary ray queries in 3D. Our method provides faithful approximations of visibility, depth, and appearance attributes.
  arXiv  Detail & Related papers  (2024-05-25T13:54:34Z)
• Linear Anchored Gaussian Mixture Model for Location and Width Computations of Objects in Thick Line Shape [1.7205106391379021]
  3D image gray level representation is considered as a finite mixture model of a statistical distribution. Expectation-Maximization algorithm (Algo1) using the original image as input data is used to estimate the model parameters. modified EM algorithm (Algo2) is detailed.
  arXiv  Detail & Related papers  (2024-04-03T20:05:00Z)
• Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings [13.532686360047574]
  We propose to train deep neural networks to detect pairwise relationships among geometric entities in 3D objects. Experiments on a large dataset of CAD models show that, by leveraging deep learning in a geometric constraint solving pipeline, the success rate of optimization-based 3D reconstruction can be significantly improved.
  arXiv  Detail & Related papers  (2022-09-06T17:59:11Z)
• Learned Cone-Beam CT Reconstruction Using Neural Ordinary Differential Equations [8.621792868567018]
  Learned iterative reconstruction algorithms for inverse problems offer the flexibility to combine analytical knowledge about the problem with modules learned from data. In computed tomography, extending such approaches from 2D fan-beam to 3D cone-beam data is challenging due to the prohibitively high GPU memory. This paper proposes to use neural ordinary differential equations to solve the reconstruction problem in a residual formulation via numerical integration.
  arXiv  Detail & Related papers  (2022-01-19T12:32:38Z)
• Data-Driven Shadowgraph Simulation of a 3D Object [50.591267188664666]
  We are replacing the numerical code by a computationally cheaper projection based surrogate model. The model is able to approximate the electric fields at a given time without computing all preceding electric fields as required by numerical methods. This model has shown a good quality reconstruction in a problem of perturbation of data within a narrow range of simulation parameters and can be used for input data of large size.
  arXiv  Detail & Related papers  (2021-06-01T08:46:04Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

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.