Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
Siddharth Tourani, Jayaram Reddy, Sarvesh Thakur, K Madhava Krishna, Muhammad Haris Khan, N Dinesh Reddy
Abstract
With the rise in consumer depth cameras, a wealth of unlabeled RGB-D data has become available. This prompts the question of how to utilize this data for geometric reasoning of scenes. While many RGB-D registration methods rely on geometric and feature-based similarity, we take a different approach. We use cycle-consistent keypoints as salient points to enforce spatial coherence constraints during matching, improving correspondence accuracy. Additionally, we introduce a novel pose block that combines a GRU recurrent unit with transformation synchronization, blending historical and multi-view data. Our approach surpasses previous self-supervised registration methods on ScanNet and 3DMatch, even outperforming some older supervised methods. We also integrate our components into existing methods, showing their effectiveness.
BibTeX
@inproceedings{icra2024_leveragingcyclec,
title = {Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration},
author = {Siddharth Tourani and Jayaram Reddy and Sarvesh Thakur and K Madhava Krishna and Muhammad Haris Khan and N Dinesh Reddy},
booktitle = {ICRA 2024},
year = {2024}
}