# 2D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classification

arXiv: https://arxiv.org/abs/2009.11154 · HTML: https://mlsanity.com/paper/2009.11154/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters](https://mlsanity.com/paper/2203.04746/) (2022)
- [Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning](https://mlsanity.com/paper/2211.09155/) (2022)
- [PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property prediction](https://mlsanity.com/paper/2511.20362/) (2025)
- [A Deep Learning-based Global and Segmentation-based Semantic Feature Fusion Approach for Indoor Scene Classification](https://mlsanity.com/paper/2302.06432/) (2023)
- [A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Driving](https://mlsanity.com/paper/2401.15902/) (2024)
- [Machine Learning Multiscale Interactions](https://mlsanity.com/paper/2605.25710/) (2026)
- [Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification](https://mlsanity.com/paper/2404.07739/) (2024)
- [Indoor scene recognition from images under visual corruptions](https://mlsanity.com/paper/2408.13029/) (2024)
- [PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model](https://mlsanity.com/paper/2410.16545/) (2024)

## Abstract (arXiv)

Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that uses two novel layers is proposed. The first layer, Multi-Neighbourhood Graph Convolution, aims to learn a more robust geometric descriptor of the scene combining two different neighbourhoods: one in the Euclidean space and the other in the Feature space. The second proposed layer, Nearest Voxel Pooling, improves the performance of the well-known Voxel Pooling. Experimental results, using NYU-Depth-V2 and SUN RGB-D datasets, show that the proposed method outperforms the current state-of-the-art in RGB-D indoor scene classification task.