A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets

TL;DR

This paper presents a hybrid method combining diffusion-based and image-to-image translation models to improve the photorealism of synthetic datasets generated by game engines, reducing the sim2real appearance gap.

Contribution

It introduces a novel hybrid approach that leverages the strengths of both diffusion models and image translation techniques for enhanced dataset realism.

Findings

REGEN outperforms FLUX.2-4B Klein in photorealism enhancement.

Combining both models yields better realism than individual models.

The hybrid approach maintains semantic consistency while improving visual quality.

Abstract

Video game engines have been an important source for generating large volumes of visual synthetic datasets for training and evaluating computer vision algorithms that are to be deployed in the real world. While the visual fidelity of modern game engines has been significantly improved with technologies such as ray-tracing, a notable sim2real appearance gap between the synthetic and the real-world images still remains, which limits the utilization of synthetic datasets in real-world applications. In this letter, we investigate the ability of a state-of-the-art image generation and editing diffusion model (FLUX.2-4B Klein) to enhance the photorealism of synthetic datasets and compare its performance against a traditional image-to-image translation model (REGEN). Furthermore, we propose a hybrid approach that combines the strong geometry and material transformations of diffusion-based methods with the distribution-matching capabilities of image-to-image translation techniques. Through experiments, it is demonstrated that REGEN outperforms FLUX.2-4B Klein and that by combining both FLUX.2-4B Klein and REGEN models, better visual realism can be achieved compared to using each model individually, while maintaining semantic consistency. The code is available at: https://github.com/stefanos50/Hybrid-Sim2Real