Improving Visual Relation Detection using Depth Maps

Sahand Sharifzadeh, Sina Moayed Baharlou, Max Berrendorf, Rajat Koner, Volker Tresp

TL;DR: Synthetically generated depth maps can improved visual relation detection.

Abstract:

State of the art visual relation detection methods mostly rely on object information extracted from RGB images such as predicted class probabilities, 2D bounding boxes and feature maps. In this paper, we argue that the 3D positions of objects in space can provide additional valuable information about object relations. This information helps not only to detect spatial relations, such as \textit{standing behind}, but also non-spatial relations, such as \textit{holding}. Since 3D information of a scene is not easily accessible, we propose incorporating a pre-trained RGB-to-Depth model within visual relation detection frameworks. We discuss different feature extraction strategies from depth maps and show their critical role in relation detection.
Our experiments confirm that the performance of state-of-the-art visual relation detection approaches can significantly be improved by utilizing depth map information.

Keywords: Visual Relation Detection, Scene Graph Generation

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1905.00966/code)