Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing

TL;DR

This paper introduces a new dataset and a contrastive fine-tuning method enabling the classification of 3D-printed objects without retraining, enhancing automation in additive manufacturing workflows.

Contribution

The paper presents ThingiPrint, a dataset for 3D-printed object classification, and demonstrates a rotation-invariant contrastive fine-tuning approach that generalizes to unseen objects without retraining.

Findings

Contrastive fine-tuning improves classification accuracy on new objects.

The approach outperforms standard pretrained models.

It enables practical, retraining-free classification in industrial settings.

Abstract

Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stages of the printing pipeline, this task still relies heavily on manual inspection, as the set of objects to be classified can change daily, making frequent model retraining impractical. Automating the identification step is therefore critical for improving operational efficiency. A vision model that could classify any set of objects by utilizing their corresponding CAD models and avoiding retraining would be highly beneficial in this setting. To enable systematic evaluation of vision models on this task, we introduce ThingiPrint, a new publicly available dataset that pairs CAD models with real photographs of their 3D-printed counterparts. Using ThingiPrint, we benchmark a range of existing vision models on the task of 3D-printed object classification. We additionally show that contrastive fine-tuning with a rotation-invariant objective allows effective prototype-based classification of previously unseen 3D-printed objects. By relying solely on the available CAD models, this avoids the need for retraining when new objects are introduced. Experiments show that this approach outperforms standard pretrained baselines, suggesting improved generalization and practical relevance for real-world use.