A grid-point detection method based on U-net for a structured light system

TL;DR

This paper introduces a U-net based grid-point detection method for structured light systems, improving accuracy in feature point detection crucial for 3D reconstruction.

Contribution

It presents a novel U-net based approach and a specialized dataset for effective grid-point detection in structured light systems.

Findings

Higher detection accuracy compared to previous methods

Effective use of a custom dataset with two-shot and one-shot images

Improved performance in 3D reconstruction tasks

Abstract

Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is designed that includes the images captured with the two-shot imaging method and the ones acquired with the one-shot imaging method. Among them, the images in the first group after labeled as the ground truth images and the images captured at the same pose with the one-shot method are cut into small patches with the size of 64x64 pixels then feed to the training set. The remaining of the images in the second group is the test set. The experimental results show that our method can achieve a better detecting performance with higher accuracy in comparison with the previous methods.