文献类型：期刊文献

英文题名：FSFSPLATTER: BUILD SURFACE AND NOVEL VIEWS WITH SPARSE-VIEWS WITHIN 3MIN

作者：Zhao, Yibin[1]; Pan, Yihan[1]; Nan, Jun[1]; Yi, Jianjun[1]

机构：[1] School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China

年份：2025

外文期刊名：arXiv

收录：EI(收录号：20250471300)

语种：英文

外文关键词：Image reconstruction - Optimization - Surface reconstruction

摘要：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. Reconstructing from free sparse images often leads to poor surface due to limited overlap and overfitting. We introduce FSFSplatter, a new approach for fast surface reconstruction from free sparse images. Our method integrates end-to-end dense Gaussian initialization, camera parameter estimation, 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 self-splitting Gaussian head. It eliminates local floaters through contribution-based pruning and mitigates overfitting to limited views by leveraging depth and multi-view feature supervision with differentiable camera parameters during rapid optimization. FSFSplatter outperforms current state-of-the-art methods on widely used DTU and Replica. ? 2025, CC BY-NC-ND.