# SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction

arXiv: https://arxiv.org/abs/2511.14633 · HTML: https://mlsanity.com/paper/2511.14633/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2025.

## Built on by (most cited first, 4 of 4)

- [Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction](https://mlsanity.com/paper/2605.12494/) (2026)
- [From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information](https://mlsanity.com/paper/2606.20842/) (2026)
- [GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors](https://mlsanity.com/paper/2608.12203/) (2026)
- [GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splatting](https://mlsanity.com/paper/2608.29346/) (2026)

## Abstract (arXiv)

Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to suboptimal reconstruction quality. Existing approaches address this challenge by employing flattened Gaussian primitives to better fit surface geometry, combined with depth regularization to alleviate geometric ambiguities under limited viewpoints. Nevertheless, the increased anisotropy inherent in flattened Gaussians exacerbates overfitting in sparse-view scenarios, hindering accurate surface fitting and degrading novel view synthesis performance. In this paper, we propose net, a method that reconstructs more accurate and detailed surfaces while preserving high-quality novel view rendering. Our key insight is to introduce Stereo Geometry-Texture Alignment, which bridges rendering quality and geometry estimation, thereby jointly enhancing both surface reconstruction and view synthesis. In addition, we present a Pseudo-Feature Enhanced Geometry Consistency that enforces multi-view geometric consistency by incorporating both training and unseen views, effectively mitigating overfitting caused by sparse supervision. Extensive experiments on the DTU, BlendedMVS, and Mip-NeRF360 datasets demonstrate that our method achieves the state-of-the-art performance.