ContRail: A Framework for Realistic Railway Image Synthesis using ControlNet

TL;DR

ContRail introduces a novel railway image synthesis framework leveraging ControlNet and multi-modal conditioning to generate realistic images, enhancing railway-specific tasks like semantic segmentation and reducing data dependency.

Contribution

This work presents the first application of ControlNet for railway image synthesis, improving the realism and utility of synthetic data for railway domain tasks.

Findings

Enhanced railway image realism through ContRail.

Improved railway semantic segmentation performance.

Synthetic data reduces need for real data in railway tasks.

Abstract

Deep Learning became an ubiquitous paradigm due to its extraordinary effectiveness and applicability in numerous domains. However, the approach suffers from the high demand of data required to achieve the potential of this type of model. An ever-increasing sub-field of Artificial Intelligence, Image Synthesis, aims to address this limitation through the design of intelligent models capable of creating original and realistic images, endeavour which could drastically reduce the need for real data. The Stable Diffusion generation paradigm recently propelled state-of-the-art approaches to exceed all previous benchmarks. In this work, we propose the ContRail framework based on the novel Stable Diffusion model ControlNet, which we empower through a multi-modal conditioning method. We experiment with the task of synthetic railway image generation, where we improve the performance in rail-specific tasks, such as rail semantic segmentation by enriching the dataset with realistic synthetic images.