GeoSVR：馴服稀疏體素以實現幾何精確的表面重建

摘要

近年來，基於輻射場的精確表面重建取得了顯著進展。然而，主要依賴於高斯潑濺的主流方法，其表現能力正日益受到瓶頸限制。本文提出GeoSVR，一種顯式的基於體素的框架，旨在探索並拓展稀疏體素在實現精確、細緻且完整表面重建方面尚未充分挖掘的潛力。稀疏體素的優勢在於支持保持覆蓋完整性和幾何清晰度，但同時也因缺乏場景約束和局部表面細化而面臨挑戰。為確保場景的正確收斂，我們首先提出了一種體素不確定性深度約束，該約束在最大化單目深度線索效應的同時，引入體素導向的不確定性以避免質量下降，從而實現有效且魯棒的場景約束，同時保持高度精確的幾何形態。隨後，設計了稀疏體素表面正則化，以增強微小體素的幾何一致性，並促進基於體素的銳利且精確表面的形成。大量實驗表明，在多樣化的挑戰性場景中，相較於現有方法，我們的方法在幾何精度、細節保留和重建完整性方面均表現出卓越性能，同時保持高效性。代碼可在https://github.com/Fictionarry/GeoSVR獲取。

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：馴服稀疏體素以實現幾何精確的表面重建

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

摘要

Support