高斯雕刻：通过场优化实现端到端可控的表面重建
Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization
- Dalian University of Technology（大连理工大学）
- Massey University（梅西大学）
- Peking University（北京大学）
- University of Nottingham Ningbo China（宁波诺丁汉大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对3DGS在视角有限时表面重建精度不足且几何误差难校正的问题，本文提出高斯雕刻框架，通过双层训练策略结合多分辨率细分方案实现高质量可控表面重建。
AI中文摘要：
3D高斯溅射（3DGS）技术近期已实现了高质量的实时新视图合成，但在视角有限的情况下，该技术难以恢复精确的表面，且由于高斯基元固有的不规则性，由此产生的几何误差极难手动校正。为解决这些问题，本文提出了一种用于高质量表面重建的全可微端到端框架——高斯雕刻（Gaussian Sculpting）。核心思路是将高斯锚定在不断演化的可微表面上，使其能够引导有符号距离场（SDF）优化，而非仅在后期处理阶段提取表面。为在联合优化过程中实现稳定的梯度隔离，本文设计了一种双层训练策略：外层循环优化由SDF表示的几何结构，内层循环则在固定几何结构的前提下更新高斯参数。此外，本文对高斯参数施加约束以确保其与底层表面的一致性，从而在优化过程中提升几何和外观保真度；还引入了一种基于类八叉树划分的多分辨率细分方案，以在保留精细细节的同时降低内存消耗。在对象级场景上的实验表明，该方法可有效去除冗余表面，恢复因视角有限导致的缺失结构，即便在相对较低的分辨率下也能实现出色的重建质量。
英文摘要：
3D Gaussian Splatting (3DGS) has recently enabled real-time novel view synthesis with impressive quality. However, it struggles to recover accurate surfaces under limited viewpoints and due to the inherent irregularity of Gaussian primitives. The resulting geometric errors are notoriously difficult to correct manually. To address these issues, we propose Gaussian Sculpting, a fully differentiable end-to-end framework for high-quality surface reconstruction. Our key insight is to anchor Gaussians onto an evolving differentiable surface, allowing them to guide signed distance field (SDF) optimization instead of extracting the surface only during post-processing. To enable stable gradient isolation during joint optimization, we design a bi-level training strategy in which the outer loop optimizes the geometry represented by the SDF, while the inner loop updates the Gaussians with the geometry fixed. We further impose constraints on Gaussian parameters to ensure consistency with the underlying surface, thereby improving both geometric and appearance fidelity during optimization. In addition, we introduce a multi-resolution subdivision scheme based on octree-like partitioning to preserve fine details while reducing memory consumption. Experiments on object-level scenes demonstrate that our method effectively removes redundant surfaces, recovers missing structures caused by limited viewpoints, and achieves strong reconstruction quality even at relatively low resolutions.
