发表机构
HIT (Shenzhen); Tsinghua University; NWPU; Beijing Institute of Control and Engineering; Technical University of Munich（哈尔滨工业大学（深圳）; 清华大学; 西北工业大学; 北京控制与工程研究所; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SurfSVR将2D表面先验作为3D几何正则化项，通过结构化2D先验提升至3D约束重建，在3个公开基准上实现了稀疏体素重建的最优效果。
AI 中文摘要
稀疏体素重建为高保真3D建模提供了高效的表示方式，但其几何结构通常是从局部光度证据和离散可见性统计中优化得到的，这往往会导致表面碎片化、过度细分以及漂浮伪影，尤其是在纹理较弱或观测稀疏的区域。我们提出了SurfSVR，一种新颖的稀疏体素重建范式，将2D表面先验作为显式的3D几何正则化项。SurfSVR不会直接提升有噪声的逐像素深度预测，而是首先通过联合推理外观、单目深度、法向量和跨视图几何，将每张图像组织为连贯的表面区域。随后，基于拟合可靠性和几何复杂度，为每个区域选择自适应的平面或二次曲面模型，同时通过模型间的一致性区分可靠几何与模糊预测。这些结构化的2D先验被提升至3D空间并整合到整个重建流程中，它们引导表面自适应的体素细分，在优化过程中提供区域级的深度和法向量监督，在体素剪枝中增强稀疏观测区域中几何可靠的表面，并在精化后训练中抑制表面外的漂浮物。这种统一设计将图像空间中的语义和几何一致性转化为3D空间中的持久结构约束。在3个公开基准上开展的大量实验表明，SurfSVR在可见性和几何特征差异显著的场景中均能持续提升稀疏体素重建的效果，达到了当前最优的重建质量。代码和模型将很快发布。
英文摘要
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.
