• Home
  • Search
  • Joint Multi-view 2D Convolutional Neural Networks for 3D Object Classification
  • Cite Icon14
  • https://doi.org/10.24963/ijcai.2020/443Copy DOI Icon

Joint Multi-view 2D Convolutional Neural Networks for 3D Object Classification

  • Jul 1, 2020
  • Jinglin Xu +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Three-dimensional (3D) object classification is widely involved in various computer vision applications, e.g., autonomous driving, simultaneous localization and mapping, which has attracted lots of attention in the committee. However, solving 3D object classification by directly employing the 3D convolutional neural networks (CNNs) generally suffers from high computational cost. Besides, existing view-based methods cannot better explore the content relationships between views. To this end, this work proposes a novel multi-view framework by jointly using multiple 2D-CNNs to capture discriminative information with relationships as well as a new multi-view loss fusion strategy, in an end-to-end manner. Specifically, we utilize multiple 2D views of a 3D object as input and integrate the intra-view and inter-view information of each view through the view-specific 2D-CNN and a series of modules (outer product, view pair pooling, 1D convolution, and fully connected transformation). Furthermore, we design a novel view ensemble mechanism that selects several discriminative and informative views to jointly infer the category of a 3D object. Extensive experiments demonstrate that the proposed method is able to outperform current state-of-the-art methods on 3D object classification. More importantly, this work provides a new way to improve 3D object classification from the perspective of fully utilizing well-established 2D-CNNs.

Similar Papers
  • Supplementary Content

Parametric Procedural Models for 3D Object Retrieval, Classification and Parameterization

  • Apr 18, 2019
  • Roman Getto
  • PDF
  • Research Article
  • Citations50

CNN-based 3D object classification using Hough space of LiDAR point clouds

  • May 07, 2020
  • Human-centric Computing and Information Sciences
  • Wei Song +5
  • Research Article
  • Citations25

Learning in the dark: 3D integral imaging object recognition in very low illumination conditions using convolutional neural networks

  • Sep 14, 2018
  • OSA Continuum
  • Adam Markman +1
  • Conference Article
  • Citations9

3D Object Categorization and Recognition based on Deep Belief Networks and Point Clouds

  • Jan 01, 2016
  • Fatima Zahra Ouadiay +3
  • Conference Article
  • Citations16

3D object recognition using 2D moments and HMLP network

  • Jul 26, 2004
  • Mohd Yusoff Mashor +2
  • Research Article
  • Citations10

Deep convolutional neural network for three-dimensional objects classification using off-axis digital Fresnel holography

  • Jun 11, 2022
  • Journal of Modern Optics
  • B Lokesh Reddy +2
  • Research Article
  • Citations20

Three-dimensional object feature extraction and classification with computational holographic imaging.

  • Jan 10, 2004
  • Applied Optics
  • Sekwon Yeom +1
  • Research Article
  • Citations77

Multi-View Saliency Guided Deep Neural Network for 3-D Object Retrieval and Classification

  • Oct 03, 2019
  • IEEE Transactions on Multimedia
  • He-Yu Zhou +3
  • Conference Article
  • Citations6

3D object recognition system using multiple views and cascaded multilayered perceptron network

  • Dec 01, 2004
  • M.K Osman +2
  • Research Article

A vectorized spherical convolutional network for recognizing 3D mesh models with unknown rotation

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Zhang Qiang +2
  • Research Article
  • Citations24

I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jiahua Dong +4
  • Research Article
  • Citations11

Survey and Evaluation of Neural 3D Shape Classification Approaches.

  • Jan 01, 2021
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Martin Mirbauer +3
  • Research Article

3D object classification based on deep belief networks and point clouds

  • Jan 01, 2019
  • International Journal of Computational Vision and Robotics
  • Majid Mohamed Himmi +4
  • PDF
  • Research Article
  • Citations17

Multi-View Hierarchical Fusion Network for 3D Object Retrieval and Classification

  • Jan 01, 2019
  • IEEE Access
  • An-An Liu +5
  • PDF
  • Research Article
  • Citations11

A Deep Learning Method for 3D Object Classification and Retrieval Using the Global Point Signature Plus and Deep Wide Residual Network

  • Apr 09, 2021
  • Sensors (Basel, Switzerland)
  • Long Hoang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.