Deep Models for Multi-View 3D Object Recognition: A Review

TL;DR

This review paper discusses recent advances in deep learning and transformer-based multi-view 3D object recognition methods, emphasizing their architectures, datasets, and performance in classification and retrieval tasks.

Contribution

It provides a comprehensive overview of current multi-view 3D recognition models, datasets, strategies, and future research directions in the field.

Findings

Multi-view approaches outperform single-view methods in 3D recognition.

Transformer-based models achieve state-of-the-art performance.

Key datasets and strategies are identified for future research.

Abstract

Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed by a single image may not be sufficient for accurate decision-making, particularly in complex recognition problems. The utilization of multi-view 3D representations for object recognition has thus far demonstrated the most promising results for achieving state-of-the-art performance. This review paper comprehensively covers recent progress in multi-view 3D object recognition methods for 3D classification and retrieval tasks. Specifically, we focus on deep learning-based and transformer-based techniques, as they are widely utilized and have achieved state-of-the-art performance. We provide detailed information about existing deep learning-based and transformer-based multi-view 3D object recognition models, including the most commonly used 3D datasets, camera configurations and number of views, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance on 3D classification and 3D retrieval tasks. Additionally, we examine various computer vision applications that use multi-view classification. Finally, we highlight key findings and future directions for developing multi-view 3D object recognition methods to provide readers with a comprehensive understanding of the field.