GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm

TL;DR

GAFAR introduces a fast, lightweight graph-attention network that enhances point descriptors at inference time, improving robustness and accuracy in rigid point cloud registration, especially under challenging conditions like outliers and low overlap.

Contribution

It proposes a novel attention-based architecture that augments point features during inference, enabling robust registration without extensive training or complex preprocessing.

Findings

Robust to outliers and low overlap

Efficient in runtime and resource consumption

Effective on various registration and generalization tasks

Abstract

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like ICP and its many variants can provide adequate solutions. In absence of a suitable initialization and in the presence of a high outlier rate or in the case of small overlap though the task of rigid registration still presents great challenges. The advent of deep learning in computer vision has brought new drive to research on this topic, since it provides the possibility to learn expressive feature-representations and provide one-shot estimates instead of depending on time-consuming iterations of conventional robust methods. Yet, the rotation and permutation invariant nature of point clouds poses its own challenges to deep learning, resulting in loss of performance and low generalization capability due to sensitivity to outliers and characteristics of 3D scans not present during network training. In this work, we present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors at inference time to optimally suit the registration task of the specific point clouds it is presented with. Employing a fully-connected graph both within and between point clouds lets the network reason about the importance and reliability of points for registration, making our approach robust to outliers, low overlap and unseen data. We test the performance of our registration algorithm on different registration and generalization tasks and provide information on runtime and resource consumption. The code and trained weights are available at https://github.com/mordecaimalignatius/GAFAR/.