GeoSVR：驾驭稀疏体素实现几何精确的表面重建

摘要

近年来，利用辐射场重建精确表面取得了显著进展。然而，当前主流方法主要基于高斯泼溅技术，正日益受到表示瓶颈的限制。本文提出GeoSVR，一种显式的基于体素的框架，探索并拓展了稀疏体素在实现精确、细致且完整表面重建方面尚未充分挖掘的潜力。稀疏体素的优势在于支持保持覆盖完整性和几何清晰度，但同时也因缺乏场景约束和局部表面细化而面临挑战。为确保场景正确收敛，我们首先提出了一种体素不确定性深度约束，该约束在最大化单目深度线索效果的同时，引入体素导向的不确定性以避免质量下降，从而实现有效且鲁棒的场景约束，同时保持高度精确的几何形状。随后，设计了稀疏体素表面正则化，以增强微小体素的几何一致性，并促进基于体素的锐利且精确表面的形成。大量实验表明，在多种具有挑战性的场景中，我们的方法相较于现有技术展现出卓越性能，在几何精度、细节保留和重建完整性方面表现优异，同时保持了高效率。代码可在https://github.com/Fictionarry/GeoSVR获取。

English

Reconstructing accurate surfaces with radiance fields has achieved remarkable progress in recent years. However, prevailing approaches, primarily based on Gaussian Splatting, are increasingly constrained by representational bottlenecks. In this paper, we introduce GeoSVR, an explicit voxel-based framework that explores and extends the under-investigated potential of sparse voxels for achieving accurate, detailed, and complete surface reconstruction. As strengths, sparse voxels support preserving the coverage completeness and geometric clarity, while corresponding challenges also arise from absent scene constraints and locality in surface refinement. To ensure correct scene convergence, we first propose a Voxel-Uncertainty Depth Constraint that maximizes the effect of monocular depth cues while presenting a voxel-oriented uncertainty to avoid quality degradation, enabling effective and robust scene constraints yet preserving highly accurate geometries. Subsequently, Sparse Voxel Surface Regularization is designed to enhance geometric consistency for tiny voxels and facilitate the voxel-based formation of sharp and accurate surfaces. Extensive experiments demonstrate our superior performance compared to existing methods across diverse challenging scenarios, excelling in geometric accuracy, detail preservation, and reconstruction completeness while maintaining high efficiency. Code is available at https://github.com/Fictionarry/GeoSVR.

GeoSVR：驾驭稀疏体素实现几何精确的表面重建

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

摘要

Support