SL3D-BF: A Real-World Structured Light 3D Dataset With Background-to-Foreground Enhancement
- 19 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 9850-9864
Abstract
Deep-learning-based structured light 3D reconstruction technology (SL3D) provides excellent solutions for intelligent manufacturing. However, the scarcity of real-world datasets covering full-process data and diverse objects hampers the validation of new ideas. Moreover, limited research on dataset construction strategies, such as scene backgrounds and sample distribution, reduces network performance. We investigate the impact of background stability on foreground accuracy (BS-FA) and find a whiteboard background improved foreground prediction accuracy by up to 82% over a black background. Guided by BS-FA, we develop the SL3D-BF, a background-effective SL3D dataset for industrial use, featuring approximately 2,100 scenes with diverse objects like metal/plastic workpieces, plaster sculptures, and standard parts for precise evaluation. It uniquely includes shadow and foreground masks, absent in prior datasets, and offers full-process data from gratings to 3D point clouds, totaling 100,800 gratings. We also establish an initial benchmark for future research by conducting evaluation experiments with advanced methods. Furthermore, we investigate the relationship between the spatial frequency of sample occurrence and the model predictive ability to minimize the time and resource demands of dataset construction. Most importantly, SL3D-BF is also a valuable resource for tasks like depth estimation, defect detection, and semantic segmentation. The dataset is available at: https://github.com/LiYiMingM/Dataset_SL3D_BF.Keywords
Funding Information
- Shenzhen Stable Supporting Program, China (WDZC20200820200655001)
- Major Key Project of Pengcheng Laboratory (PCL2023A09)
This publication has 41 references indexed in Scilit:
- Novel approach for fast structured light framework using deep learningImage and Vision Computing, 2024
- Global phase accuracy enhancement of structured light system calibration and 3D reconstruction by overcoming inevitable unsatisfactory intensity modulationMeasurement, 2024
- Towards local visual modeling for image captioningPattern Recognition, 2023
- Two-dimensional phase unwrapping by a high-resolution deep learning networkMeasurement, 2022
- PU-M-Net for phase unwrapping with speckle reduction and structure protection in ESPIOptics and Lasers in Engineering, 2022
- Deep absolute phase recovery from single-frequency phase map for handheld 3D measurementOptics Communications, 2022
- A novel projector ray-model for 3D measurement in fringe projection profilometryOptics and Lasers in Engineering, 2022
- Flexible and high-accuracy method for uni-directional structured light system calibrationOptics and Lasers in Engineering, 2021
- Optical fringe patterns filtering based on multi-stage convolution neural networkOptics and Lasers in Engineering, 2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015