# DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration

arXiv: https://arxiv.org/abs/2206.05707 · HTML: https://mlsanity.com/paper/2206.05707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 79 references that are in the map.
- First posted on arXiv 12 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [3DRegNet: A Deep Neural Network for 3D Point Registration](https://mlsanity.com/paper/1904.01701/) (2019)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [PCRNet: Point Cloud Registration Network using PointNet Encoding](https://mlsanity.com/paper/1908.07906/) (2019)
- [Learning Deep Similarity Metric for 3D MR-TRUS Registration](https://mlsanity.com/paper/1806.04548/) (2018)
- [Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations](https://mlsanity.com/paper/2107.10296/) (2021)
- [An Artificial Agent for Robust Image Registration](https://mlsanity.com/paper/1611.10336/) (2016)
- [RSL-Net: Localising in Satellite Images From a Radar on the Ground](https://mlsanity.com/paper/2001.03233/) (2020)
- [Deep Learning based Inter-Modality Image Registration Supervised by Intra-Modality Similarity](https://mlsanity.com/paper/1804.10735/) (2018)
- [Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information](https://mlsanity.com/paper/1909.03752/) (2019)
- [PHASER: a Robust and Correspondence-free Global Pointcloud Registration](https://mlsanity.com/paper/2102.02767/) (2021)
- [AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects](https://mlsanity.com/paper/1910.04668/) (2019)
- [Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching](https://mlsanity.com/paper/2008.09474/) (2020)
- [A Two-Stream Symmetric Network with Bidirectional Ensemble for Aerial Image Matching](https://mlsanity.com/paper/2002.01325/) (2020)
- [Semi-Supervised Deep Metrics for Image Registration](https://mlsanity.com/paper/1804.01565/) (2018)

## Abstract (arXiv)

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.