Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation

TL;DR

This paper demonstrates how Pix2Pix GANs can generate realistic ground truth images from abstract maps, aiding urban planning and autonomous vehicle data creation by producing high-fidelity, paired datasets.

Contribution

It introduces a novel application of Pix2Pix for transforming abstract maps into realistic images, with a tailored training process and a new paired dataset.

Findings

High-fidelity urban feature rendering

Effective transformation of abstract maps to realistic images

Potential for broad real-world applications

Abstract

Generative Adversarial Networks (GANs) have significantly advanced image processing, with Pix2Pix being a notable framework for image-to-image translation. This paper explores a novel application of Pix2Pix to transform abstract map images into realistic ground truth images, addressing the scarcity of such images crucial for domains like urban planning and autonomous vehicle training. We detail the Pix2Pix model's utilization for generating high-fidelity datasets, supported by a dataset of paired map and aerial images, and enhanced by a tailored training regimen. The results demonstrate the model's capability to accurately render complex urban features, establishing its efficacy and potential for broad real-world applications.