Deep Global Registration
This addresses the challenge of accurate 3D scan alignment for applications like robotics and computer vision, representing an incremental improvement over existing techniques.
The paper tackles the problem of pairwise registration of real-world 3D scans by introducing Deep Global Registration, a differentiable framework that outperforms state-of-the-art methods on real-world data.
We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.