Triangle Splatting+：使用不透明三角形的可微渲染
Triangle Splatting+: Differentiable Rendering with Opaque Triangles
AI总结：
本文提出Triangle Splatting+，通过可微泼溅框架直接优化共享顶点的不透明三角形，无需后处理即可生成兼容标准图形引擎的网格，并在多个基准上达到基于网格新视角合成的最优效果。
摘要：
近年来，三维场景重建与新视角合成取得了快速进展。Neural Radiance Fields（神经辐射场）证明连续体辐射场能够实现高质量图像合成，但其漫长的训练与渲染时间限制了实用性。3D Gaussian Splatting（3DGS，三维高斯泼溅）通过使用数百万个高斯函数表示场景解决了这些问题，支持实时渲染和快速优化。然而，高斯图元本身并不兼容VR头显及实时图形应用所采用的基于网格的管线。现有方案尝试通过后处理或两阶段管线将高斯函数转换为网格，这既增加了复杂性，又降低了视觉质量。在本研究中，我们提出Triangle Splatting+，在可微泼溅框架内直接优化计算机图形学的基础图元——三角形。我们构建了三角形参数化方法，通过共享顶点实现连通性，并设计了强制使用不透明三角形的训练策略。最终输出无需后处理即可直接用于标准图形引擎。在Mip-NeRF360和Tanks & Temples数据集上的实验表明，Triangle Splatting+在基于网格的新视角合成中达到了最先进性能。我们的方法在视觉保真度上超越此前的泼溅方法，同时保持高效且训练快速。此外，生成的半连通网格支持基于物理的仿真或交互式漫游等下游应用。项目页面为https://trianglesplatting2.github.io/trianglesplatting2/。
英文摘要：
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 & 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/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
