mlsanityData to 14 Oct 2026

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes

arXiv 2512.04421 ↗First posted 4 Dec 2025cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Ray tracing 3D Gaussian particles enables realistic effects such as depth of field, refractions, and flexible camera modeling for novel-view synthesis. However, existing methods trace Gaussians through proxy geometry, which requires constructing complex intermediate meshes and performing costly intersection tests. This limitation arises because Gaussian-based particles are not well suited as unified primitives for both ray tracing and rasterization. In this work, we propose a differentiable triangle-based ray tracing pipeline that directly treats triangles as rendering primitives without relying on any proxy geometry. Our results show that the proposed method achieves significantly higher rendering quality than existing ray tracing approaches while maintaining real-time rendering performance. Moreover, our pipeline can directly render triangles optimized by the rasterization-based method Triangle Splatting, thus unifying the primitives used in novel-view synthesis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

29 of 39 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  7. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  8. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  9. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  10. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  11. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  12. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
17 more
  1. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  2. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  3. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
  4. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  5. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
  6. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
  7. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
  8. 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
  9. 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 88
  10. 2024IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracingcited by 54
  11. 2025Triangle Splatting for Real-Time Radiance Field Renderingcited by 50
  12. 2024Reflective Gaussian Splattingcited by 42
  13. 2024EnvGS: Modeling View-Dependent Appearance with Environment Gaussiancited by 35
  14. 2024BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesiscited by 25
  15. 2024PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relightingcited by 18
  16. 20252D Triangle Splatting for Direct Differentiable Mesh Trainingcited by 5
  17. 2024PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfercited by 4

Built on by

Not cited yet.