基于稀疏视角的神经表面重建与极几何
Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry
AI总结：
本文提出EpiS框架，利用极几何改进稀疏视角下的表面重建，通过epipolar transformer和射线聚合生成SDF-aware特征，结合几何正则化策略提升重建精度。
摘要：
从稀疏多视角图像中准确重建表面仍具挑战性，因存在严重几何歧义和遮挡。现有通用神经表面重建方法主要依赖成本体积，使用简单统计信息（如均值和方差）总结多视角特征，丢弃关键视角依赖的几何结构，导致过度平滑的重建。本文提出EpiS框架，通过显式利用极几何处理稀疏视角输入。EpiS不直接从成本体积统计回归几何，而是利用粗略成本体积特征指导沿对应极线采样细粒度极特征的聚合。epipolar transformer融合多视角信息，随后通过射线聚合生成SDF-aware特征进行表面估计。为进一步缓解稀疏视角下的信息损失，引入几何正则化策略，利用预训练单目深度模型通过尺度不变的全局和局部约束。在DTU和BlendedMVS上的大量实验表明，EpiS在稀疏视角设置下显著优于现有最先进的通用表面重建方法，同时保持强泛化性，无需每场景优化。
英文摘要：
Reconstructing accurate surfaces from sparse multi-view images remains challenging due to severe geometric ambiguity and occlusions. Existing generalizable neural surface reconstruction methods primarily rely on cost volumes that summarize multi-view features using simple statistics (e.g., mean and variance), which discard critical view-dependent geometric structure and often lead to over-smoothed reconstructions. We propose EpiS, a generalizable neural surface reconstruction framework that explicitly leverages epipolar geometry for sparse-view inputs. Instead of directly regressing geometry from cost-volume statistics, EpiS uses coarse cost-volume features to guide the aggregation of fine-grained epipolar features sampled along corresponding epipolar lines across source views. An epipolar transformer fuses multi-view information, followed by ray-wise aggregation to produce SDF-aware features for surface estimation. To further mitigate information loss under sparse views, we introduce a geometry regularization strategy that leverages a pretrained monocular depth model through scale-invariant global and local constraints. Extensive experiments on DTU and BlendedMVS demonstrate that EpiS significantly outperforms state-of-the-art generalizable surface reconstruction methods under sparse-view settings, while maintaining strong generalization without per-scene optimization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
