GS2Mesh：通过新颖立体视图从高斯溅射进行表面重建
GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views
AI总结：
提出GS2Mesh，通过预训练立体匹配模型从3DGS渲染的立体视图提取深度并融合为网格，实现更平滑、精确的表面重建，在野外场景及Tanks and Temples、DTU基准上达到最先进水平。
摘要：
近年来，3D高斯溅射（3DGS）已成为准确表示场景的高效方法。然而，尽管其在新视角合成方面表现出色，直接从高斯属性中提取场景几何仍然是一个挑战，因为这些属性是基于光度损失进行优化的。虽然一些并行模型尝试在高斯优化过程中添加几何约束，但它们仍会产生噪声大、不真实的表面。我们提出了一种新颖的方法，通过将真实世界知识注入深度提取过程，弥合噪声3DGS表示与平滑3D网格表示之间的差距。我们不直接从高斯属性中提取场景几何，而是通过预训练的立体匹配模型提取几何。我们渲染与原始训练姿态对应的立体对齐图像对，将图像对输入立体模型以获得深度剖面，最后将所有剖面融合以生成单个网格。与从高斯溅射进行表面重建的其他方法相比，所得重建更平滑、更准确，并显示出更复杂的细节，同时仅在相当短的3DGS优化过程之上增加少量开销。我们在使用智能手机获取的野外场景上对所提方法进行了广泛测试，展示了其卓越的重建能力。此外，我们在Tanks and Temples和DTU基准上测试了该方法，取得了最先进的结果。
英文摘要：
Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. However, despite its superior novel view synthesis capabilities, extracting the geometry of the scene directly from the Gaussian properties remains a challenge, as those are optimized based on a photometric loss. While some concurrent models have tried adding geometric constraints during the Gaussian optimization process, they still produce noisy, unrealistic surfaces. We propose a novel approach for bridging the gap between the noisy 3DGS representation and the smooth 3D mesh representation, by injecting real-world knowledge into the depth extraction process. Instead of extracting the geometry of the scene directly from the Gaussian properties, we instead extract the geometry through a pre-trained stereo-matching model. We render stereo-aligned pairs of images corresponding to the original training poses, feed the pairs into a stereo model to get a depth profile, and finally fuse all of the profiles together to get a single mesh. The resulting reconstruction is smoother, more accurate and shows more intricate details compared to other methods for surface reconstruction from Gaussian Splatting, while only requiring a small overhead on top of the fairly short 3DGS optimization process. We performed extensive testing of the proposed method on in-the-wild scenes, obtained using a smartphone, showcasing its superior reconstruction abilities. Additionally, we tested the method on the Tanks and Temples and DTU benchmarks, achieving state-of-the-art results.
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。
