MVSGaussian：基于多视图立体的快速可泛化高斯泼溅重建
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
AI总结：
该研究提出MVSGaussian可泛化3D高斯重建方法，结合MVS几何编码、混合渲染与几何一致性聚合策略，实现了更优质量的实时渲染与快速单场景微调，在多个数据集上达到SOTA性能。
摘要：
我们提出MVSGaussian，这是一种源自多视图立体（Multi-View Stereo, MVS）的新型可泛化3D高斯表示方法，能够高效重建未见过的场景。具体而言：1）我们利用MVS编码具备几何感知的高斯表示，并将其解码为高斯参数。2）为进一步提升性能，我们提出混合高斯渲染方法，整合了高效的体渲染设计以用于新视图合成。3）为支持针对特定场景的快速微调，我们引入多视图几何一致性聚合策略，有效聚合由可泛化模型生成的点云，作为单场景优化的初始化。 此前基于可泛化NeRF的方法通常需要数分钟的微调时间，且渲染单张图像需数秒；相比之下，MVSGaussian实现了实时渲染，且每个场景的合成质量更优。与原生3D-GS相比，MVSGaussian以更低的训练计算成本实现了更好的视图合成效果。在DTU、Real Forward-facing、NeRF Synthetic以及Tanks and Temples数据集上的大量实验验证，MVSGaussian取得了当前最优性能，具备出色的泛化能力、实时渲染速度以及快速的单场景优化能力。
英文摘要：
We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization.
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。
