# MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks

## TL;DR

This paper introduces MV-C3D, a multi-view 3D CNN that effectively recognizes objects from partial viewpoints by learning spatially correlated features, outperforming existing methods especially in real-world scenarios.

## Contribution

The paper proposes a novel multi-view 3D CNN model that handles partial viewpoints and learns spatial correlations, improving 3D object recognition accuracy in practical settings.

## Key findings

- Achieves high accuracy on ModelNet10 and ModelNet40 datasets.
- Demonstrates robustness with partial view images from less range.
- Outperforms existing methods in real-world scenarios on MIRO dataset.

## Abstract

As the development of deep neural networks, 3D object recognition is becoming increasingly popular in computer vision community. Many multi-view based methods are proposed to improve the category recognition accuracy. These approaches mainly rely on multi-view images which are rendered with the whole circumference. In real-world applications, however, 3D objects are mostly observed from partial viewpoints in a less range. Therefore, we propose a multi-view based 3D convolutional neural network, which takes only part of contiguous multi-view images as input and can still maintain high accuracy. Moreover, our model takes these view images as a joint variable to better learn spatially correlated features using 3D convolution and 3D max-pooling layers. Experimental results on ModelNet10 and ModelNet40 datasets show that our MV-C3D technique can achieve outstanding performance with multi-view images which are captured from partial angles with less range. The results on 3D rotated real image dataset MIRO further demonstrate that MV-C3D is more adaptable in real-world scenarios. The classification accuracy can be further improved with the increasing number of view images.