FSFSplatter：两分钟内从自由稀疏视角图像实现几何精确重建
FSFSplatter: Geometrically Accurate Reconstruction with Free Sparse-view Images within 2 minutes
用大 Transformer 从自由稀疏视角图像端到端回归稠密且几何一致的高斯初始化，配合基于贡献度的剪枝与深度/多视图特征监督，在 2 分钟内完成重建；对做稀疏视角 3DGS 与无位姿重建的人，这套「前馈初始化 + 可微相机参数」流程可直接复用。
原文依据 generates a dense and geometrically consistent Gaussian scene initialization via a batch based self-splitting Gaussian head
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高斯泼溅已成为一种领先的重建技术，以高质量的新视角合成和细节丰富的重建著称。然而，现有方法大多需要稠密且已标定的视角。从自由稀疏视角图像进行重建时，由于视角重叠有限和过拟合，往往导致表面质量较差。我们提出 FSFSplatter，用于从自由稀疏视角图像快速实现几何精确的重建。该方法将端到端的稠密高斯场景初始化与几何增强的场景优化相结合。具体而言，FSFSplatter 采用大型 Transformer 对多视图图像进行编码，并通过基于批处理的自分裂高斯头生成稠密且几何一致的高斯场景初始化。它通过基于贡献度的剪枝消除局部漂浮物，并借助深度与多视图特征监督以及可微相机参数来缓解过拟合，整个过程在两分钟内完成。FSFSplatter 在广泛使用的 DTU、Replica 和 BlendedMVS 数据集上优于当前最优方法。
英文原文摘要 1058 字符
Gaussian Splatting has become a leading reconstruction technique, known for its high-quality novel view synthesis and detailed reconstruction. However, most existing methods require dense, calibrated views. Reconstruction from free sparse-view images often leads to poor surface due to limited overlap and overfitting.We introduce FSFSplatter for fast geometrically accurate reconstruction from free sparse-view images. Our method integrates end-to-end dense Gaussian scene initialization and geometry-enhanced scene optimization.Specifically, FSFSplatter employs a large transformer to encode multi-view images and generates a dense and geometrically consistent Gaussian scene initialization via a batch based self-splitting Gaussian head. It eliminates local floaters through contribution-based pruning and mitigates overfitting by leveraging depth and multi-view feature supervision, along with differentiable camera parameters within 2 minutes.FSFSplatter outperforms current state-of-the-art methods on widely used DTU, Replica, and BlendedMVS datasets.