{"ID":2863823,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25122","arxiv_id":"2509.25122","title":"Triangle Splatting+: Differentiable Rendering with Opaque Triangles","abstract":"Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can achieve high-quality image synthesis, but their long training and rendering times limit practicality. 3D Gaussian Splatting (3DGS) addressed these issues by representing scenes with millions of Gaussians, enabling real-time rendering and fast optimization. However, Gaussian primitives are not natively compatible with the mesh-based pipelines used in VR headsets, and real-time graphics applications. Existing solutions attempt to convert Gaussians into meshes through post-processing or two-stage pipelines, which increases complexity and degrades visual quality. In this work, we introduce Triangle Splatting+, which directly optimizes triangles, the fundamental primitive of computer graphics, within a differentiable splatting framework. We formulate triangle parametrization to enable connectivity through shared vertices, and we design a training strategy that enforces opaque triangles. The final output is immediately usable in standard graphics engines without post-processing. Experiments on the Mip-NeRF360 and Tanks \u0026 Temples datasets show that Triangle Splatting+achieves state-of-the-art performance in mesh-based novel view synthesis. Our method surpasses prior splatting approaches in visual fidelity while remaining efficient and fast to training. Moreover, the resulting semi-connected meshes support downstream applications such as physics-based simulation or interactive walkthroughs. The project page is https://trianglesplatting2.github.io/trianglesplatting2/.","short_abstract":"Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can achieve high-quality image synthesis, but their long training and rendering times limit practicality. 3D Gaussian Splatting (3DGS) addressed t...","url_abs":"https://arxiv.org/abs/2509.25122","url_pdf":"https://arxiv.org/pdf/2509.25122v1","authors":"[\"Jan Held\",\"Renaud Vandeghen\",\"Sanghyun Son\",\"Daniel Rebain\",\"Matheus Gadelha\",\"Yi Zhou\",\"Ming C. Lin\",\"Marc Van Droogenbroeck\",\"Andrea Tagliasacchi\"]","published":"2025-09-29T17:43:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}