MeshGS：用于高质量渲染的自适应网格对齐高斯泼溅
MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering
AI总结：
提出MeshGS方法，通过基于距离的对齐技术将3D Gaussian splats与网格表面结合，实现高质量真实场景渲染，PSNR显著提升且Gaussian splats数量减少30%。
摘要：
最近，3D Gaussian splatting 因其生成高保真渲染结果的能力而备受关注。同时，诸如游戏、动画和 AR/VR 等大多数应用使用基于网格的表示来表示和渲染 3D 场景。我们提出了一种将网格表示与 3D Gaussian splats 相结合的新方法，以对重建的真实世界场景进行高质量渲染。具体而言，我们引入了一种基于距离的 Gaussian splatting 技术，将 Gaussian splats 与网格表面对齐，并移除对渲染没有贡献的冗余 Gaussian splats。我们考虑每个 Gaussian splat 与网格表面之间的距离，以区分紧密绑定和松散绑定的 Gaussian splats。紧密绑定的 splats 被展平并与网格几何形状良好对齐。松散绑定的 Gaussian splats 用于在渲染方面弥补重建 3D 网格中的伪影。我们提出了一种将 Gaussian splats 绑定到网格几何形状的训练策略，并兼顾这两种类型的 splats。在此背景下，我们引入了几种正则化技术，旨在训练过程中将紧密绑定的 Gaussian splats 与网格表面精确对齐。我们在 mip-NeRF 360 和 Deep Blending 数据集的大型无边界场景上验证了该方法的有效性。我们的方法超越了近期基于网格的神经渲染技术，实现了高 2dB 的 PSNR，并且比基于网格的 Gaussian splatting 方法高出 1.3 dB PSNR，特别是在室外 mip-NeRF 360 数据集上，展现了更好的渲染质量。我们对每种类型的 Gaussian splat 进行了分析，并与原始 3D Gaussian splatting 相比，将 Gaussian splats 的数量减少了 30%。
英文摘要：
Recently, 3D Gaussian splatting has gained attention for its capability to generate high-fidelity rendering results. At the same time, most applications such as games, animation, and AR/VR use mesh-based representations to represent and render 3D scenes. We propose a novel approach that integrates mesh representation with 3D Gaussian splats to perform high-quality rendering of reconstructed real-world scenes. In particular, we introduce a distance-based Gaussian splatting technique to align the Gaussian splats with the mesh surface and remove redundant Gaussian splats that do not contribute to the rendering. We consider the distance between each Gaussian splat and the mesh surface to distinguish between tightly-bound and loosely-bound Gaussian splats. The tightly-bound splats are flattened and aligned well with the mesh geometry. The loosely-bound Gaussian splats are used to account for the artifacts in reconstructed 3D meshes in terms of rendering. We present a training strategy of binding Gaussian splats to the mesh geometry, and take into account both types of splats. In this context, we introduce several regularization techniques aimed at precisely aligning tightly-bound Gaussian splats with the mesh surface during the training process. We validate the effectiveness of our method on large and unbounded scene from mip-NeRF 360 and Deep Blending datasets. Our method surpasses recent mesh-based neural rendering techniques by achieving a 2dB higher PSNR, and outperforms mesh-based Gaussian splatting methods by 1.3 dB PSNR, particularly on the outdoor mip-NeRF 360 dataset, demonstrating better rendering quality. We provide analyses for each type of Gaussian splat and achieve a reduction in the number of Gaussian splats by 30% compared to the original 3D Gaussian splatting.
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。
