3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation

• URL: http://arxiv.org/abs/2608.17298v1
• Date: Tue, 18 Aug 2026 02:50:46 GMT
• Title: 3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation
• Abstract summary: 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.
• Score: 0.00270839927451854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D Gaussian Splatting has made Gaussian primitives a highly efficient representation for real-time novel view synthesis, but its rasterisation-based formulation relies on screen-space approximations that limit accurate view-dependent ordering and the integration of secondary ray effects such as reflections, refractions, and shadows. Gaussian ray tracing addresses these limitations by evaluating explicit ray-primitive intersections, yet it remains costly to train. We observe that the main bottleneck is not ray traversal alone, but the pixel-centric backward propagation, where many threads concurrently accumulate gradients into the same primitive parameters, causing severe atomic contention and thread serialisation. We present 3DGART, a practical training framework for ray-traced Gaussian rendering. Our key idea is to reorganise backward propagation around primitives rather than pixels. Using conservative perspective-correct screen-space bounds, we build a compact intermediate buffer and a tile-primitive mapping that allows each thread to accumulate the contribution of one primitive over its covered pixels within a tile. This transforms gradient computation from a contention-heavy scatter operation into a structured gather-like process. On Mip-NeRF 360, 3DGART achieves an $\approx 3-3.5\times$ raw training speedup over per-pixel baseline and $\approx4 \times$ over 3DGRT on Mip-NeRF 360 while improving quality. More importantly, 3DGART makes fully ray-traced Gaussian training practical, reaching runtimes competitive with rasterisation-based pipelines while preserving benefits of ray tracing.

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)
• Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting [13.614076961940647]
  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.
  arXiv  Detail & Related papers  (2026-03-24T18:23:12Z)
• 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)
• 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)
• AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius [38.774337140911044]
  3D Gaussian Splatting (3DGS) is a recent explicit 3D representation that has achieved high-quality reconstruction and real-time rendering of complex scenes. We propose AdR-Gaussian, which moves part of serial culling in Render stage into the earlier Preprocess stage to enable parallel culling. Our contributions are threefold, achieving a rendering speed of 310% while maintaining equivalent or even better quality than the state-of-the-art.
  arXiv  Detail & Related papers  (2024-09-13T09:32:38Z)
• 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes [50.36933474990516]
  This work considers ray tracing the particles, building a bounding volume hierarchy and casting a ray for each pixel using high-performance ray tracing hardware. To efficiently handle large numbers of semi-transparent particles, we describe a specialized algorithm which encapsulates particles with bounding meshes. Experiments demonstrate the speed and accuracy of our approach, as well as several applications in computer graphics and vision.
  arXiv  Detail & Related papers  (2024-07-09T17:59:30Z)
• 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)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)

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.