发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Sparse-GS2Mesh，利用对极深度初始化3DGS并引入自适应基线选择、立体匹配微调和2D/3D联合正则化，在稀疏视图下实现高质量表面重建，低重叠设置中较最先进方法提升15%。
AI 中文摘要
在稀疏视图设置下的表面重建仍然具有挑战性，因为几何线索有限。基于符号距离函数的体渲染方法通常会产生过度平滑的表面，而3D高斯泼溅（3DGS）虽然时间效率高，但由于缺乏可靠的深度监督以及仅从给定输入视图优化的限制，会导致几何不完整。在本文中，我们提出了Sparse-GS2Mesh，一种用于从稀疏视图进行表面重建的立体感知框架。虽然3DGS和立体匹配已被利用于密集视图设置下的表面重建，我们将其扩展到在稀疏视图条件下有效运行，首先使用对极深度先验初始化3DGS以缓解3DGS过拟合问题，然后是我们的三个关键组件：（I）自适应基线选择，（II）使用立体匹配网络进行微调，以及（III）2D/3D联合正则化微调。给定用对极深度初始化的预热3DGS，自适应基线选择自动确定为每个稀疏视图合成的基线。然后我们通过从立体匹配网络反向传播深度细化梯度来微调3DGS，有效地使3DGS专门用于立体匹配。2D/3D联合正则化进一步有助于获得稳定的重建，解决近距离立体视图中弱几何线索的问题。Sparse-GS2Mesh在低重叠设置中比最先进方法实现了15%的改进，在高重叠设置中取得了可比的结果。代码将公开提供。
英文摘要
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.
CommentsAccepted to NIPS 2026 PhysWorldAI workshops. Project Page: https://yhnoh8623.github.io/projects/s-gs2mesh/
