A Review and Efficient Implementation of Scene Graph Generation Metrics


Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years. However, despite these strides, precise and thorough definitions for the metrics used to evaluate scene graph generation models are lacking. In this paper, we address this gap in the literature by providing a review and precise definition of commonly used metrics in scene graph generation. Our comprehensive examination clarifies the underlying principles of these metrics and can serve as a reference or introduction to scene graph metrics. Furthermore, to facilitate the usage of these metrics, we introduce a standalone Python package called SGBench that efficiently implements all defined metrics, ensuring their accessibility to the research community. Additionally, we present a scene graph benchmarking web service, that enables researchers to compare scene graph generation methods and increase visibility of new methods in a central place.


Precise Definitions of Scene Graph Metrics

We rigorously define the following scene graph metrics using pseudo code and equations:

Python Package

The code to calculate the described metrics is bundled as an easy to install pip package. It has only four dependencies in total and should work with any big framework you are currently using.

You can install the python package using

    pip install sgbench

The source code will be made available here: https://github.com/lorjul/sgbench

Benchmarking Server

To compare recent scene graph methods, we developed a benchmarking server where users can upload scene graph evaluation files.


The structure of this page is taken and modified from nvlabs.github.io/eg3d which was published under the Creative Commons CC BY-NC 4.0 license .