MVIP -- A Dataset and Methods for Application Oriented Multi-View and Multi-Modal Industrial Part Recognition

TL;DR

MVIP introduces a comprehensive multi-modal, multi-view dataset tailored for industrial part recognition, aiming to advance transferability, modality fusion, and synthetic data generation methods for practical industrial applications.

Contribution

The paper presents MVIP, a novel dataset combining calibrated RGBD multi-view data with object context, and establishes a benchmark for application-oriented industrial part recognition challenges.

Findings

MVIP enables evaluation of multi-modal recognition methods.

The dataset highlights challenges like limited data and similar-looking parts.

It facilitates research on modality fusion and synthetic data in industrial contexts.

Abstract

We present MVIP, a novel dataset for multi-modal and multi-view application-oriented industrial part recognition. Here we are the first to combine a calibrated RGBD multi-view dataset with additional object context such as physical properties, natural language, and super-classes. The current portfolio of available datasets offers a wide range of representations to design and benchmark related methods. In contrast to existing classification challenges, industrial recognition applications offer controlled multi-modal environments but at the same time have different problems than traditional 2D/3D classification challenges. Frequently, industrial applications must deal with a small amount or increased number of training data, visually similar parts, and varying object sizes, while requiring a robust near 100% top 5 accuracy under cost and time constraints. Current methods tackle such challenges individually, but direct adoption of these methods within industrial applications is complex and requires further research. Our main goal with MVIP is to study and push transferability of various state-of-the-art methods within related downstream tasks towards an efficient deployment of industrial classifiers. Additionally, we intend to push with MVIP research regarding several modality fusion topics, (automated) synthetic data generation, and complex data sampling -- combined in a single application-oriented benchmark.