Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2603.23637v2
• Date: Thu, 26 Mar 2026 12:01:55 GMT
• Title: Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting
• Abstract summary: We present a differentiable, sorting-free formulation for ray-traced 3DGS.<n>For standard 3DGS, our method matches the reconstruction quality and speed of sorting-based 3DGS.<n>For relightable 3DGS, the same estimator drives per-Gaussian shading with fully ray-traced shadow rays.
• Score: 13.614076961940647
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work.

Related papers

• ConeGaussian: Anti-Aliased Gaussian Ray-Tracing for Generic Central Cameras [56.46810752790842]
  We present ConeGaussian, a camera-model-agnostic anti-aliasing framework for Gaussian ray-based rendering.<n>We derive a closed-form response under a locally linear, depth-local, moment-matched approximation of the finite pixel footprint.<n>Unlike in mip-splatting, our scene-space frequency floor and filtering enable trivial composition at render time, allowing us to remove excess blurring.
  arXiv  Detail & Related papers  (2026-09-11T18:05:07Z)
• 3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation [0.00270839927451854]
  We present 3DGART, a practical training framework for ray-traced Gaussian rendering.<n>Our key idea is to reorganise backward propagation around primitives rather than pixels.<n>On Mip-NeRF 360, 3DGART achieves an $approx 3-3.5times$ raw training speedup over per-pixel baseline.
  arXiv  Detail & Related papers  (2026-08-18T02:50:46Z)
• Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration [7.536387580547838]
  3D Gaussian Splatting (3DGS) has been widely adopted as a geometric proxy that bridges LiDAR and camera within a single differentiable framework.<n>We propose a framework that preserves the metric geometry of the Gaussian proxy by aggregating multi-view LiDAR observations.<n>We validate our method on public driving datasets, where it consistently outperforms existing targetless methods in calibration accuracy.
  arXiv  Detail & Related papers  (2026-06-18T11:23:33Z)
• Radioactive 3D Gaussian Ray Tracing for Tomographic Reconstruction [10.822437634828303]
  R2-Gaussian extended the 3DGS paradigm to tomographic reconstruction.<n>We propose a tomographic reconstruction framework based on 3D Gaussian ray tracing.
  arXiv  Detail & Related papers  (2026-02-01T06:53:42Z)
• GRTX: Efficient Ray Tracing for 3D Gaussian-Based Rendering [4.541956402929217]
  We present GRTX, a set of software and hardware optimizations that enable efficient ray tracing for 3D Gaussian-based rendering.<n>First, we introduce a novel approach for constructing streamlined acceleration structures for Gaussian primitives.<n>Second, we propose dedicated hardware support for checkpointing within ray tracing units.<n>Our evaluation shows that GRTX significantly improves ray tracing performance compared to the baseline with a negligible hardware cost.
  arXiv  Detail & Related papers  (2026-01-28T09:37:12Z)
• UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes [1.633289883726582]
  Ray tracing 3D Gaussian particles enables realistic effects such as depth of field refractions, and flexible camera modeling for novel-view rendering.<n>Existing methods trace Gaussians through triangle geometry, which requires constructing complex intermediate meshes and performing costly tests.<n>We propose a differentiable triangle-based ray tracing pipeline that treats triangles as rendering primitives without relying on any proxy geometry.
  arXiv  Detail & Related papers  (2025-12-04T03:33:10Z)
• PSRGS:Progressive Spectral Residual of 3D Gaussian for High-Frequency Recovery [3.310033172069517]
  3D Gaussian Splatting (3D GS) achieves impressive results in novel view synthesis for small, single-object scenes.<n>However, when applied to large-scale remote sensing scenes, 3D GS faces challenges.<n>We propose PSRGS, a progressive optimization scheme based on spectral residual maps.
  arXiv  Detail & Related papers  (2025-03-02T10:52:46Z)
• RaySplats: Ray Tracing based Gaussian Splatting [6.808029514985239]
  3D Gaussian Splatting (3DGS) is a process that enables the direct creation of 3D objects from 2D images.<n>This paper introduces RaySplats, a model that employs ray-tracing based Splatting.
  arXiv  Detail & Related papers  (2025-01-31T15:05:06Z)
• Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels [51.08794269211701]
  We introduce 3D Linear Splatting (3DLS), which replaces Gaussian kernels with linear kernels to achieve sharper and more precise results.<n>3DLS demonstrates state-of-the-art fidelity and accuracy, along with a 30% FPS improvement over baseline 3DGS.
  arXiv  Detail & Related papers  (2024-11-19T11:59:54Z)
• GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [69.67264955234494]
  GeoSplatting is a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling.<n>By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface.<n>This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T17:57:07Z)
• Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering [47.879695094904015]
  We present a novelview rendering algorithm, Mode-GS, for ground-robot trajectory datasets. Our approach is based on using anchored Gaussian splats, which are designed to overcome the limitations of existing 3D Gaussian splatting algorithms. Our method results in improved rendering performance, based on PSNR, SSIM, and LPIPS metrics, in ground scenes with free trajectory patterns.
  arXiv  Detail & Related papers  (2024-10-06T23:01:57Z)
• 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)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.<n>We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images.<n>We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)

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.