Pose registration is critical in vision and robotics. This paper focuses on the challenging task of initialization-free pose registration up to 7DoF for homogeneous and heterogeneous measurements. While recent learning-based methods show promise using differentiable solvers, they either rely on heuristically defined correspondences or are prone to local minima. We present a differentiable phase correlation (DPC) solver that is globally convergent and correspondence-free. When combined with simple feature extraction networks, our general framework DPCN++ allows for versatile pose registration with arbitrary initialization. Specifically, the feature extraction networks first learn dense feature grids from a pair of homogeneous/heterogeneous measurements. These feature grids are then transformed into a translation and scale invariant spectrum representation based on Fourier transform and spherical radial aggregation, decoupling translation and scale from rotation. Next, the rotation, scale, and translation are independently and efficiently estimated in the spectrum step-by-step using the DPC solver. The entire pipeline is differentiable and trained end-to-end. We evaluate DCPN++ on a wide range of registration tasks taking different input modalities, including 2D bird's-eye view images, 3D object and scene measurements, and medical images. Experimental results demonstrate that DCPN++ outperforms both classical and learning-based baselines, especially on partially observed and heterogeneous measurements.

翻译：观光和机器人的注册至关重要。 本文侧重于不初始化的难度性任务 7DoF 的注册, 包括同质/ 异质测量。 虽然最近的学习方法显示使用不同溶剂的前景, 但它们要么依赖超常定义的通信, 要么依赖于本地迷你。 我们展示了一个全球趋同和无往来的可区别阶段相关(DPC)解析器。 当与简单的地物提取网络相结合时, 我们的总框架 DPCN++ 允许以任意初始化的形式进行多种功能的注册。 具体地说, 地物提取网络首先从一对同质/ 异质测量中学习密集的特征网格。 这些功能网格随后在四面变异变异的变异频谱代表制和球状的拼凑基础上转换成一个翻译和比例, 解开全球趋异的翻译和缩缩缩缩放。 下一步, 旋转、 规模和翻译是独立和高效地在频谱逐步地使用基于 DPC 解算器的解算器进行快速注册。 整个管道是可区分和经过培训的最终端端端端端端端端端端。 我们评估了一组的DPN+++B, 的登记任务,,,,, 包括了不同输入和正级模型的图像, 和正态图像,,,,,,, 和正版图图图图图,,,,,,,,, 和正版图, 。