Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering
Not on the map. Why?
Abstract (arXiv)
Recent radiance field methods represent scenes with 2D primitives that offer surface alignment and efficient rasterization, from Gaussian disks to triangles, yet all rely on convex boundaries: curved and concave structures demand excessive primitives. We introduce Deformable Triangle Splatting, which augments each triangle with K control points per edge, each parameterized by a single learnable scalar displacement that shifts the boundary inward or outward, enabling non-convex shape representation while preserving the three base vertices that define the 3D plane. To render these non-convex primitives differentiably, we design a rasterization pipeline in the triangle's barycentric coordinate space, ensuring view-consistent rendering. A winding number test determines whether each pixel lies inside the deformed primitive, and a window function controlled by two learnable parameters, sharpness and corner smoothness, together with a per-primitive scalar opacity, produces the smooth opacity transition from interior to boundary. Validation is done in a variety of real-world scenes, outperforming recent works based on non-volumetric primitives in terms of visual quality and versatility while still achieving competitive rendering efficiency.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 24 Jul 2026.
Builds on
44 of 53 references.
References · 44
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
32 more
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2017Neural 3D Mesh Renderercited by 437
- 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
- 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
- 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
- 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
- 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
- 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 103
- 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
- 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
- 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
- 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
- 20243D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexescited by 50
- 2025Triangle Splatting for Real-Time Radiance Field Renderingcited by 50
- 2025Deformable Beta Splattingcited by 38
- 2024GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modelingcited by 30
- 2024BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesiscited by 23
- 2024Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernelscited by 22
- 2024SpectroMotion: Dynamic 3D Reconstruction of Specular Scenescited by 21
- 2025LinPrim: Linear Primitives for Differentiable Volumetric Renderingcited by 21
- 2024Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitivescited by 20
- 2024Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Videocited by 20
- 2024Deformable Radial Kernel Splattingcited by 17
- 2023NeRF Revisited: Fixing Quadrature Instability in Volume Renderingcited by 10
- 20244DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fieldscited by 5
- 2025Universal Beta Splattingcited by 3
- 2026NeRFscopy: Neural Radiance Fields for in-vivo Time-Varying Tissues from Endoscopycited by 2
Built on by
Not cited yet.