ESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding

TL;DR

ESGNN introduces an equivariant graph neural network for 3D scene graph generation from point clouds, enhancing accuracy, robustness, and efficiency for real-time scene understanding tasks.

Contribution

This work is the first to implement an equivariant GNN for semantic scene graph generation from 3D point clouds, improving performance and computational efficiency.

Findings

ESGNN outperforms existing methods in scene estimation accuracy.

ESGNN converges faster than previous approaches.

ESGNN requires low computational resources and is easy to implement.

Abstract

Scene graphs have been proven to be useful for various scene understanding tasks due to their compact and explicit nature. However, existing approaches often neglect the importance of maintaining the symmetry-preserving property when generating scene graphs from 3D point clouds. This oversight can diminish the accuracy and robustness of the resulting scene graphs, especially when handling noisy, multi-view 3D data. This work, to the best of our knowledge, is the first to implement an Equivariant Graph Neural Network in semantic scene graph generation from 3D point clouds for scene understanding. Our proposed method, ESGNN, outperforms existing state-of-the-art approaches, demonstrating a significant improvement in scene estimation with faster convergence. ESGNN demands low computational resources and is easy to implement from available frameworks, paving the way for real-time applications such as robotics and computer vision.