Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction

📄 arXiv: 2608.11938v1 📥 PDF

作者: Yan Di, Chengxi Li, Yaoxing Wang, Mengge Liu, Zhigang Li, Ruida Zhang, Mingyang Li, Pengyuan Wang, Shan Gao, Xiangyang Ji

分类: cs.CV

发布日期: 2026-08-12

💡 一句话要点

提出SurfSVR以解决稀疏体素重建中的几何碎片化问题

🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics)

关键词: 稀疏体素重建 几何正则化 3D建模 深度学习 计算机视觉

📋 核心要点

  1. 现有稀疏体素重建方法依赖局部光度信息，导致几何碎片化和漂浮伪影，尤其在纹理稀疏区域表现不佳。
  2. SurfSVR通过将2D表面先验作为3D几何正则化器，结合多种信息共同推理，提升了重建的几何一致性。
  3. 在多个公共基准测试上，SurfSVR在不同场景下均表现出色，显著提高了重建质量，达到了最先进的水平。

📝 摘要（中文）

稀疏体素重建为高保真3D建模提供了高效表示，但其几何形状通常依赖于局部光度证据和离散可见性统计，导致表面碎片化、过度细分和漂浮伪影，尤其在纹理稀疏或观察不足的区域。本文提出SurfSVR，一种新颖的稀疏体素重建范式，将2D表面先验视为显式的3D几何正则化器。SurfSVR通过联合推理外观、单目深度、法线和跨视图几何，首先将每幅图像组织成一致的表面区域，并根据拟合可靠性和几何复杂性自适应选择平面或二次曲面模型。通过将这些结构化的2D先验提升至3D并整合到重建流程中，SurfSVR显著改善了稀疏体素重建的质量。

🔬 方法详解

问题定义：本文旨在解决稀疏体素重建中因依赖局部光度证据而导致的几何碎片化和漂浮伪影问题。现有方法在纹理稀疏或观察不足的区域表现不佳，影响重建质量。

核心思路：SurfSVR的核心思想是将2D表面先验作为显式的3D几何正则化器，通过联合推理多种信息（如外观、单目深度、法线和跨视图几何），组织图像为一致的表面区域，从而提升重建的几何一致性。

技术框架：SurfSVR的整体架构包括几个主要模块：首先，图像被组织为一致的表面区域；其次，根据拟合可靠性和几何复杂性选择平面或二次曲面模型；最后，将这些2D先验提升至3D并整合到重建流程中，指导体素细分和优化。

关键创新：SurfSVR的主要创新在于将2D表面先验引入3D重建流程，形成了一个统一的设计，能够将图像空间中的语义和几何一致性转化为3D中的结构约束。这一方法与传统依赖局部信息的重建方法本质上不同。

关键设计：在关键设计上，SurfSVR采用自适应选择的表面模型，结合区域级深度和法线监督，优化过程中引入了结构化的2D先验，增强了几何可靠性，并在后期细化训练中抑制漂浮伪影。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在多个公共基准测试中，SurfSVR在不同场景下的稀疏体素重建质量显著提升，达到了最先进的水平，具体性能数据表明，相较于基线方法，重建质量提高了XX%，在某些场景中甚至提升了XX%。

🎯 应用场景

SurfSVR在高保真3D建模、虚拟现实、增强现实等领域具有广泛的应用潜力。通过提高稀疏体素重建的质量，该方法能够为各种视觉计算任务提供更可靠的几何信息，推动相关技术的发展。

📄 摘要（原文）

Sparse voxel reconstruction offers an efficient representation for high-fidelity 3D modeling, yet its geometry is commonly optimized from local photometric evidence and discrete visibility statistics. This often leads to fragmented surfaces, excessive subdivision, and floating artifacts, particularly in weakly textured or sparsely observed regions. We introduce SurfSVR, a novel sparse voxel reconstruction paradigm that treats 2D surface priors as explicit 3D geometric regularizers. Instead of directly lifting noisy pixel-wise depth predictions, SurfSVR first organizes each image into coherent surface regions by jointly reasoning over appearance, monocular depth, normals and cross-view geometry. Each region is then represented by an adaptively selected planar or quadratic surface model based on fitting reliability and geometric complexity, while cross-model agreement distinguishes reliable geometry from ambiguous predictions. These structured 2D priors are lifted into 3D and integrated throughout the reconstruction pipeline. They guide surface-adaptive voxel subdivision, provide region-level depth and normal supervision during optimization, enhance geometrically reliable sparse-observed surfaces in voxel pruning, and suppress off-surface floaters during post-refinement training. This unified design converts semantic and geometric coherence in image space into persistent structural constraints in 3D. Extensive experiments on 3 public benchmarks demonstrate that SurfSVR consistently improves sparse voxel reconstruction across scenes with substantially different visibility and geometry characteristics, achieving state-of-the-art reconstruction quality. Codes and models will be released soon.