Semi-Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing

TL;DR

This paper introduces a Semi-Siamese deep learning model for robust, real-time defect detection in 3D printing, capable of handling diverse imaging conditions and outperforming complex existing methods.

Contribution

A novel Semi-Siamese network architecture for defect detection that compares reference schematics with achieved prints, robust across different domains and imaging perturbations.

Findings

Achieves over 0.9 F1-score in defect localization.

Operates in less than half a second per layer on standard hardware.

Outperforms state-of-the-art GAN and transformer-based methods.

Abstract

Automatic defect detection for 3D printing processes, which shares many characteristics with change detection problems, is a vital step for quality control of 3D printed products. However, there are some critical challenges in the current state of practice. First, existing methods for computer vision-based process monitoring typically work well only under specific camera viewpoints and lighting situations, requiring expensive pre-processing, alignment, and camera setups. Second, many defect detection techniques are specific to pre-defined defect patterns and/or print schematics. In this work, we approach the defect detection problem using a novel Semi-Siamese deep learning model that directly compares a reference schematic of the desired print and a camera image of the achieved print. The model then solves an image segmentation problem, precisely identifying the locations of defects of different types with respect to the reference schematic. Our model is designed to enable comparison of heterogeneous images from different domains while being robust against perturbations in the imaging setup such as different camera angles and illumination. Crucially, we show that our simple architecture, which is easy to pre-train for enhanced performance on new datasets, outperforms more complex state-of-the-art approaches based on generative adversarial networks and transformers. Using our model, defect localization predictions can be made in less than half a second per layer using a standard MacBook Pro while achieving an F1-score of more than 0.9, demonstrating the efficacy of using our method for in-situ defect detection in 3D printing.