Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification
This addresses the problem of missing local geometric context in depth-based methods for researchers in computer vision and robotics, representing a strong domain-specific advancement.
The paper tackles geometric 3D scene classification by proposing a Residual Attention Graph Convolutional Network that exploits intrinsic geometric context without point features, achieving state-of-the-art results on NYU Depth v1 and SUN-RGBD datasets.
Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to missing local geometric context in the depth channel. This work proposes a novel Residual Attention Graph Convolutional Network that exploits the intrinsic geometric context inside a 3D space without using any kind of point features, allowing the use of organized or unorganized 3D data. Experiments are done in NYU Depth v1 and SUN-RGBD datasets to study the different configurations and to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed method outperforms current state-of-the-art in geometric 3D scene classification tasks.