Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps

TL;DR

This paper introduces a fast, accurate, and object boundary-aware surface normal estimation method from depth maps, suitable for real-time applications, by formulating a closed-form solution and noise reduction techniques.

Contribution

A novel surface normal estimation approach that is both efficient and robust to noise, with explicit handling of depth discontinuities, outperforming existing algorithms.

Findings

Outperforms baseline algorithms in accuracy

Operates in real-time due to computational efficiency

Effectively reduces errors at depth discontinuities

Abstract

This paper proposes a fast and accurate surface normal estimation method which can be directly used on depth maps (organized point clouds). The surface normal estimation process is formulated as a closed-form expression. In order to reduce the effect of measurement noise, the averaging operation is utilized in multi-direction manner. The multi-direction normal estimation process is reformulated in the next step to be implemented efficiently. Finally, a simple yet effective method is proposed to remove erroneous normal estimation at depth discontinuities. The proposed method is compared to well-known surface normal estimation algorithms. The results show that the proposed algorithm not only outperforms the baseline algorithms in term of accuracy, but also is fast enough to be used in real-time applications.