F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimization

TL;DR

F2M-Reg introduces an unsupervised RGB-D point cloud registration method that uses a neural implicit scene model for robust global registration, outperforming previous methods especially under challenging conditions.

Contribution

The paper proposes a novel frame-to-model optimization framework leveraging neural implicit fields for robust unsupervised RGB-D registration, addressing inconsistencies in traditional frame-to-frame methods.

Findings

Outperforms state-of-the-art methods on four benchmarks.

More robust to lighting changes, occlusion, and low overlap.

Uses synthetic warming-up with a photorealistic dataset.

Abstract

This work studies the problem of unsupervised RGB-D point cloud registration, which aims at training a robust registration model without ground-truth pose supervision. Existing methods usually leverages unposed RGB-D sequences and adopt a frame-to-frame framework based on differentiable rendering to train the registration model, which enforces the photometric and geometric consistency between the two frames for supervision. However, this frame-to-frame framework is vulnerable to inconsistent factors between different frames, e.g., lighting changes, geometry occlusion, and reflective materials, which leads to suboptimal convergence of the registration model. In this paper, we propose a novel frame-to-model optimization framework named F2M-Reg for unsupervised RGB-D point cloud registration. We leverage the neural implicit field as a global model of the scene and optimize the estimated poses of the frames by registering them to the global model, and the registration model is subsequently trained with the optimized poses. Thanks to the global encoding capability of neural implicit field, our frame-to-model framework is significantly more robust to inconsistent factors between different frames and thus can provide better supervision for the registration model. Besides, we demonstrate that F2M-Reg can be further enhanced by a simplistic synthetic warming-up strategy. To this end, we construct a photorealistic synthetic dataset named Sim-RGBD to initialize the registration model for the frame-to-model optimization on real-world RGB-D sequences. Extensive experiments on four challenging benchmarks have shown that our method surpasses the previous state-of-the-art counterparts by a large margin, especially under scenarios with severe lighting changes and low overlap. Our code and models are available at https://github.com/MrIsland/F2M_Reg.