Sparse-GS2Mesh: 3D Gaussian Splatting Guided by Novel Stereo Views and 2DGS for Sparse View Surface Reconstruction}

2026-10-03

AI Summary

This study addresses the over-smoothing and structural loss in sparse-view surface reconstruction caused by insufficient geometric cues. We propose a stereo-aware 3D Gaussian Splatting (3DGS) framework that introduces a novel epipolar depth prior initialization strategy, combined with adaptive baseline selection and stereo matching fine-tuning. Furthermore, a 2D/3D collaborative regularization scheme is incorporated to effectively mitigate the overfitting and supervision scarcity inherent in conventional methods under sparse-view settings. Experimental results demonstrate that our approach outperforms state-of-the-art methods by 15% in low-overlap scenarios while maintaining comparable performance in high-overlap cases, significantly improving the quality of sparse-view 3D reconstruction.

Abstract

Surface reconstruction under sparse-view settings remains challenging due to limited geometric cues. Volume rendering methods based on signed distance functions often produce over-smoothed surfaces, while 3D Gaussian Splatting (3DGS), though time-efficient, suffers from incomplete geometry due to the lack of reliable depth supervision and the limitation of being optimized only from given input views. In this paper, we present Sparse-GS2Mesh, a stereo-aware framework for surface reconstruction from sparse views. While 3DGS and stereo matching have been leveraged for surface reconstruction under dense view settings, we extend them to operate effectively under sparse view conditions by first initializing 3DGS using epipolar depth priors to mitigate the 3DGS overfitting problem, followed by our three key components: (I) adaptive baseline selection, (II) fine-tuning with a stereo matching network, and (III) 2D/3D co-regularized fine-tuning. Given a warmed-up 3DGS initialized with epipolar depth, the adaptive baseline selection automatically determines a baseline to synthesize for each sparse view. We then fine-tune 3DGS by backpropagating depth-refining gradients from the stereo matching network, effectively specializing the 3DGS for stereo matching. The 2D/3D co-regularization further helps obtain stable reconstruction, addressing weak geometric cues in close stereo views. Sparse-GS2Mesh achieves a 15\% improvement over state-of-the-art methods in little-overlap settings and comparable results in large-overlap settings. Codes will be publicly available.

Problem

• Sparse View Surface Reconstruction
• 3D Gaussian Splatting
• Depth Supervision
• Geometric Cues

Innovation

• Sparse View Surface Reconstruction
• 3D Gaussian Splatting
• Stereo Matching
• Adaptive Baseline Selection
• 2D/3D Co-regularization