SCCM：用于ERP稠密特征对应的球面一致粗匹配
SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence
浏览论文内容
中文总结 AI 辅助
SCCM通过球面位置注意力和面积感知共可见性，在粗匹配阶段纠正ERP的拓扑、度量和面积畸变，显著提升稠密特征匹配精度并实现跨数据集泛化。
中文摘要 AI 辅助
等距柱状投影（ERP）是360°图像的标准表示形式，在ERP上进行鲁棒的稠密特征匹配支撑着全景立体视觉、视图合成和全向SLAM。在平面图像上训练的稠密匹配器在ERP上会系统性退化，因为该投影引入了三种耦合的畸变——拓扑畸变、度量畸变和面积畸变——而标准的粗匹配和可见性估计并未显式建模这些畸变。我们证明，在粗匹配阶段接口处（即注意力中的成对畸变、共可见性门控中的逐像素畸变）纠正这三种畸变，在固定粗匹配骨架且精化器架构不变的情况下，可将Matterport3D上的PCK@1°从0.229提升至0.275——这是我们的核心结果。具体而言，SCCM（球面一致粗匹配）通过两个球面先验增强了一个对投影无感知的交叉注意力/双softmax粗匹配器：球面位置注意力（SPA）将偏航周期旋转位置编码（拓扑）与切平面偏置（度量）配对，而面积感知共可见性（AAC）应用了sigmoid前的对数面积校正（面积）。对投影无感知的骨架作为受控参考，将骨架替换效应与球面先验效应分离开来。在RoMa V1框架中实例化，使用相同的冻结编码器、精化器架构和损失函数，SCCM在统一的ERP稠密匹配协议下也优于ERP原生的EDM（0.163）和经过ERP重训练的RoMa V1（0.198），而透视训练的匹配器在ERP上大多失败。它还能零样本迁移到Stanford2D3D，并且在户外Holo360D上训练时，同样在该数据集上领先。
英文摘要
Dense feature matching between 360$^\circ$ panoramas underpins omnidirectional pose estimation, 3D reconstruction, and SLAM. Such panoramas are stored in the equirectangular projection (ERP), which unrolls the viewing sphere onto a flat chart and thereby introduces three distinct distortions -- a longitudinal seam (topology), latitude-dependent stretch (metric), and non-uniform pixel area (area) -- that the coarse stage of perspective-trained dense matchers does not model, so these matchers degrade systematically on ERP. We show that correcting the three distortions at the coarse-stage interfaces where they arise -- pairwise distortions in attention, per-pixel distortion in covisibility gating -- improves PCK@1$^\circ$ from 0.230 to 0.275 on Matterport3D under a fixed coarse scaffold, with the refiner architecture unchanged -- our central result. Concretely, SCCM (Spherically Consistent Coarse Matching) augments a chart-naive cross-attention/dual-softmax coarse matcher with two sphere-derived priors: Spherical Positional Attention (SPA) pairs a yaw-periodic RoPE (topology) with a tangent-plane bias (metric), and Area-Aware Covisibility (AAC) applies a pre-sigmoid log-area correction (area). The chart-naive scaffold serves as a controlled reference, separating the scaffold-replacement effect from the spherical-prior effect. Instantiated in the RoMa V1 framework with the same frozen encoder, refiner architecture, and loss, SCCM also outperforms the ERP-native EDM (0.163) and an ERP-retrained RoMa V1 (0.198) under a unified ERP dense matching protocol, while perspective-trained matchers largely fail on ERP. It further transfers zero-shot to Stanford2D3D and, when trained on outdoor Holo360D, leads there as well.
发表机构
- Kakao Mobility Corp.（Kakao Mobility 公司）
- Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。
