CVPR Findings2026
2D Triangle Splatting for Direct Differentiable Mesh Training
Kaifeng Sheng, Zheng Zhou, Yingliang Peng, Qianwei Wang
Abstract
Differentiable rendering with 3D Gaussian primitives has emerged as a powerful method for reconstructing highfidelity 3D scenes from multi-view images. While it offers improvements over NeRF-based methods, this representation still encounters challenges with rendering speed and advanced rendering effects, such as relighting and shadow rendering, compared to mesh-based models. In this paper, we propose 2D Triangle Splatting (2DTS), a novel method that replaces 3D Gaussian primitives with 2D triangle primitives. This representation naturally forms a discrete mesh-like structure while retaining the benefits of continuous volumetric modeling. Through the incorporation and controlled annealing of a compactness parameter, our method maintains differentiability during training while producing triangle meshes with fully opaque faces at the end of optimization without the need for additional post-processing. Experimental results demonstrate that our triangle-based representation achieves competitive visual quality with Gaussian-based methods while providing a more direct bridge to mesh-based representations. Our method bridges the gap between differentiable rendering and traditional mesh-based rendering, offering a promising solution for applications requiring renderable mesh-like reconstructions.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- 2D Gaussian Splatting for Geometrically Accurate Radiance Fields cites Plenoxels: Radiance Fields without Neural Networks
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Plenoxels: Radiance Fields without Neural Networks
- Plenoxels: Radiance Fields without Neural Networks cites Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
Builds on15
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
- 2D Gaussian Splatting for Geometrically Accurate Radiance FieldsBinbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger et al.SIGGRAPH 2024 · 660 citations
Related papers
- Tetrahedron Splatting for 3D GenerationChun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu et al.NeurIPS 2024 · 13 citations
- Mani-GS: Gaussian Splatting Manipulation with Triangular MeshXiangjun Gao, Xiaoyu Li, Yiyu Zhuang, Qi Zhang et al.CVPR 2025
- MeshSplatting: Differentiable Rendering with Opaque MeshesJan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain et al.CVPR 2026 · 25 citations
- Stochastic Ray Tracing for the Reconstruction of 3D Gaussian SplattingPeiyu Xu, Shuang Zhao, Xin Sun, Krishna Mullia et al.CVPR 2026 · 1 citation
- GS-2DGS: Geometrically Supervised 2DGS for Reflective Object ReconstructionJinguang Tong, Xuesong Li, Fahira Afzal Maken, Sundaram Muthu et al.CVPR 2025
