CVROApr 1, 2024

Scalable 3D Registration via Truncated Entry-wise Absolute Residuals

arXiv:2404.00915v223 citationsh-index: 3CVPR
Originality Highly original
AI Analysis

This addresses a scalability bottleneck in computer vision for applications like robotics and augmented reality, offering a significant improvement over existing methods that fail with large datasets.

The paper tackles the problem of scalable outlier-robust 3D registration, which involves aligning 3D point pairs despite high outlier rates, and achieves the ability to process over 10 million point pairs with over 99% outliers while maintaining high accuracy and low memory usage.

Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible. This is an important problem in computer vision, for which many highly accurate approaches have been recently proposed. Despite their impressive performance, these approaches lack scalability, often overflowing the $16$GB of memory of a standard laptop to handle roughly $30,000$ point pairs. In this paper, we propose a $3$D registration approach that can process more than ten million ($10^7$) point pairs with over $99\%$ random outliers. Moreover, our method is efficient, entails low memory costs, and maintains high accuracy at the same time. We call our method TEAR, as it involves minimizing an outlier-robust loss that computes Truncated Entry-wise Absolute Residuals. To minimize this loss, we decompose the original $6$-dimensional problem into two subproblems of dimensions $3$ and $2$, respectively, solved in succession to global optimality via a customized branch-and-bound method. While branch-and-bound is often slow and unscalable, this does not apply to TEAR as we propose novel bounding functions that are tight and computationally efficient. Experiments on various datasets are conducted to validate the scalability and efficiency of our method.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes