提升点云图局部表面几何精度，解决3D重建细节失真问题
SurGe: Improved Surface Geometry in Point Maps
- 引入点法向量评估指标，显化局部几何误差
- 提出梯度匹配损失与邻域注意力解码器，改善局部结构
- 在8个零样本单目基准上实现全局与局部性能双优
近期的前馈式3D重建方法能准确预测点云图并估计全局3D结构，但局部表面几何仍存在明显偏差，这种偏差在视觉上显著，却难以被常规指标捕捉。为此，我们提出一种点云法向量评估指标，用于衡量邻近3D预测所诱导的局部表面方向。为减少此类误差，我们设计两个互补组件：深度归一化的点梯度匹配损失，监督3D有限差分；以及邻域注意力解码器（NAD），通过渐进式上采样与邻域注意力机制实现局部特征融合。在八个零样本单目几何基准上，所提模型SurGe在全局点云图的AbsRel指标上取得最佳平均排名，并持续提升局部点云图与点云法向量评估表现。
原文摘要 · Abstract (English)
Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface geometry, which is clearly visible qualitatively but only weakly reflected in common metrics. To make these errors more explicit in evaluation, we introduce a point map normal metric that evaluates the local surface orientation induced by neighboring 3D predictions. To reduce these errors, we propose two complementary components: a point gradient matching loss that supervises depth-normalized 3D finite differences, and a Neighborhood Attention Decoder (NAD) that progressively upsamples features and uses Neighborhood Attention for local feature mixing. Across eight zero-shot monocular geometry benchmarks, our model, SurGe, achieves the best average rank for global point map AbsRel and consistently improves local point map and point map normal evaluations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。