ContRail: A Framework for Realistic Railway Image Synthesis using ControlNet
This work addresses data limitations for railway image analysis tasks, but it is incremental as it builds on existing Stable Diffusion and ControlNet methods.
The authors tackled the problem of data scarcity in deep learning by proposing ContRail, a framework for generating realistic railway images using ControlNet, which improved rail semantic segmentation performance by enriching datasets with synthetic images.
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.