English

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

Computer Vision and Pattern Recognition 2025-06-24 v1 Artificial Intelligence

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 digitized herbarium specimens (a task made challenging by heterogeneous backgrounds), non-plant 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.

Keywords

Cite

@article{arxiv.2506.18683,
  title  = {SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds from RGB Images for 2D Classification},
  author = {Youcef Sklab and Hanane Ariouat and Eric Chenin and Edi Prifti and Jean-Daniel Zucker},
  journal= {arXiv preprint arXiv:2506.18683},
  year   = {2025}
}

Comments

25 pages, 9 figures, 14 tables

R2 v1 2026-07-01T03:29:33.200Z