SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds From RGB Images for 2D Classification

IF 1.5 4区 计算机科学 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Youcef Sklab, Hanane Ariouat, Eric Chenin, Edi Prifti, Jean-Daniel Zucker
{"title":"SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds From RGB Images for 2D Classification","authors":"Youcef Sklab,&nbsp;Hanane Ariouat,&nbsp;Eric Chenin,&nbsp;Edi Prifti,&nbsp;Jean-Daniel Zucker","doi":"10.1049/cvi2.70036","DOIUrl":null,"url":null,"abstract":"<p>We introduce the shape-image multimodal network (SIM-Net), a novel 2D image classification architecture that integrates 3D point cloud representations inferred directly from RGB images. Our key contribution lies in a pixel-to-point transformation that converts 2D object masks into 3D point clouds, enabling the fusion of texture-based and geometric features for enhanced classification performance. SIM-Net is particularly well-suited for the classification of digitised herbarium specimens—a task made challenging by heterogeneous backgrounds, nonplant elements, and occlusions that compromise conventional image-based models. To address these issues, SIM-Net employs a segmentation-based preprocessing step to extract object masks prior to 3D point cloud generation. The architecture comprises a CNN encoder for 2D image features and a PointNet-based encoder for geometric features, which are fused into a unified latent space. Experimental evaluations on herbarium datasets demonstrate that SIM-Net consistently outperforms ResNet101, achieving gains of up to 9.9% in accuracy and 12.3% in F-score. It also surpasses several transformer-based state-of-the-art architectures, highlighting the benefits of incorporating 3D structural reasoning into 2D image classification tasks.</p>","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70036","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Computer Vision","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cvi2.70036","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

We introduce the shape-image multimodal network (SIM-Net), a novel 2D image classification architecture that integrates 3D point cloud representations inferred directly from RGB images. Our key contribution lies in a pixel-to-point transformation that converts 2D object masks into 3D point clouds, enabling the fusion of texture-based and geometric features for enhanced classification performance. SIM-Net is particularly well-suited for the classification of digitised herbarium specimens—a task made challenging by heterogeneous backgrounds, nonplant elements, and occlusions that compromise conventional image-based models. To address these issues, SIM-Net employs a segmentation-based preprocessing step to extract object masks prior to 3D point cloud generation. The architecture comprises a CNN encoder for 2D image features and a PointNet-based encoder for geometric features, which are fused into a unified latent space. Experimental evaluations on herbarium datasets demonstrate that SIM-Net consistently outperforms ResNet101, achieving gains of up to 9.9% in accuracy and 12.3% in F-score. It also surpasses several transformer-based state-of-the-art architectures, highlighting the benefits of incorporating 3D structural reasoning into 2D image classification tasks.

Abstract Image

SIM-Net:利用RGB图像中推断的3D物体形状点云进行2D分类的多模态融合网络
我们介绍了形状-图像多模态网络(SIM-Net),这是一种新的2D图像分类架构,集成了直接从RGB图像推断的3D点云表示。我们的关键贡献在于将2D对象蒙版转换为3D点云的像素到点转换,从而实现基于纹理和几何特征的融合,从而增强分类性能。SIM-Net特别适合于数字化植物标本的分类,这是一项具有挑战性的任务,因为不同的背景、非植物元素和遮挡会损害传统的基于图像的模型。为了解决这些问题,SIM-Net采用基于分段的预处理步骤,在生成3D点云之前提取对象掩模。该架构包括一个用于二维图像特征的CNN编码器和一个用于几何特征的基于pointnet的编码器,它们融合到一个统一的潜在空间中。对植物标本馆数据集的实验评估表明,SIM-Net始终优于ResNet101,准确率提高了9.9%,F-score提高了12.3%。它还超越了几种基于变压器的最先进架构,突出了将3D结构推理纳入2D图像分类任务的好处。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IET Computer Vision
IET Computer Vision 工程技术-工程:电子与电气
CiteScore
3.30
自引率
11.80%
发文量
76
审稿时长
3.4 months
期刊介绍: IET Computer Vision seeks original research papers in a wide range of areas of computer vision. The vision of the journal is to publish the highest quality research work that is relevant and topical to the field, but not forgetting those works that aim to introduce new horizons and set the agenda for future avenues of research in computer vision. IET Computer Vision welcomes submissions on the following topics: Biologically and perceptually motivated approaches to low level vision (feature detection, etc.); Perceptual grouping and organisation Representation, analysis and matching of 2D and 3D shape Shape-from-X Object recognition Image understanding Learning with visual inputs Motion analysis and object tracking Multiview scene analysis Cognitive approaches in low, mid and high level vision Control in visual systems Colour, reflectance and light Statistical and probabilistic models Face and gesture Surveillance Biometrics and security Robotics Vehicle guidance Automatic model aquisition Medical image analysis and understanding Aerial scene analysis and remote sensing Deep learning models in computer vision Both methodological and applications orientated papers are welcome. Manuscripts submitted are expected to include a detailed and analytical review of the literature and state-of-the-art exposition of the original proposed research and its methodology, its thorough experimental evaluation, and last but not least, comparative evaluation against relevant and state-of-the-art methods. Submissions not abiding by these minimum requirements may be returned to authors without being sent to review. Special Issues Current Call for Papers: Computer Vision for Smart Cameras and Camera Networks - https://digital-library.theiet.org/files/IET_CVI_SC.pdf Computer Vision for the Creative Industries - https://digital-library.theiet.org/files/IET_CVI_CVCI.pdf
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信