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

Resource information

Authors

Stefanos Pasios

Research area

Computer vision

Application domain

General AI research

AI methods

Diffusion models, Computer vision

Research topics

cs.CV

arXiv record date

2026-05-04

Publication date

2026-05-04

Publication

arXiv

Upstream last modified

May 5, 2026

Last record update

Nov 3, 2026

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