IUP-Pose：解耦迭代不确定性传播用于通过隐式密集对齐的实时相对姿态回归
IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1
AI总结：
本文提出IUP-Pose，通过隐式密集对齐解决相对姿态估计中姿态与位移估计耦合和跨视图特征对齐不足的问题，实现高精度与高效能的实时部署。
摘要：
相对姿态估计是SLAM、视觉定位和3D重建的基础。现有相对姿态回归（RPR）方法面临关键权衡：特征匹配流水线虽然精度高但因非可微RANSAC阻断梯度流动，而基于ViT的回归器则无法满足实时部署需求。本文提出IUP-Pose，一种几何驱动的解耦迭代框架，结合隐式密集对齐。轻量级的多头双交叉注意力（MHBC）模块通过无显式匹配监督对跨视图特征进行对齐。对齐后的特征通过解耦的旋转-位移流水线处理：两个共享参数的旋转阶段通过不确定性迭代优化旋转，特征图通过旋转同构H_inf重新对齐后再进行位移预测。IUP-Pose在MegaDepth1500上实现73.3% AUC@20deg，70 FPS吞吐量和仅37M参数，展示了在实时边缘部署中的良好精度-效率权衡。
英文摘要：
Relative pose estimation is fundamental for SLAM, visual localization, and 3D reconstruction. Existing Relative Pose Regression (RPR) methods face a key trade-off: feature-matching pipelines achieve high accuracy but block gradient flow via non-differentiable RANSAC, while ViT-based regressors are end-to-end trainable but prohibitively expensive for real-time deployment. We identify the core bottlenecks as the coupling between rotation and translation estimation and insufficient cross-view feature alignment. We propose IUP-Pose, a geometry-driven decoupled iterative framework with implicit dense alignment. A lightweight Multi-Head Bi-Cross Attention (MHBC) module aligns cross-view features without explicit matching supervision. The aligned features are processed by a decoupled rotation-translation pipeline: two shared-parameter rotation stages iteratively refine rotation with uncertainty, and feature maps are realigned via rotational homography H_inf before translation prediction. IUP-Pose achieves 73.3% AUC@20deg on MegaDepth1500 with full end-to-end differentiability, 70 FPS throughput, and only 37M parameters, demonstrating a favorable accuracy-efficiency trade-off for real-time edge deployment.
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。
