Data Augmentation

Augment your data with RealSim

Apply realistic textures onto your existing RGB datasets to increase variation for perception training.

Increase variation in your training data

Real World Data

Unannotated real-world images are used to fine-tune RealSim to learn how the world looks.

Synthetic RGB frame captured in Carla

Generate Synthetic Data

Generate data in simulation to obtain synthetic images, and feed this into RealSim 

RealSim by Repli5 is a data augmentation tool to improve realism of synthetic data.

Apply RealSim

RealSim applies real-world textures on to the synthetic dataset to further stimulate the model during training.

Better results with fewer resources.

RealSim enables perception engineers to obtain more variety in their data with fewer real-world annotated images. This reduces cost without compromising model performance. 

“We’ve seen models train comparatively using RealSim data as they would using annotated images logged from the real world.”

Synthetic data industries
Prof. Devdatt Dubhashi – Chief Scientist
USE CASE

We’re developing RealSim in automotive/AD, off-road domains such as mining, and even manufacturing.

RealSim has a substantial amount of pre-trained knowledge. It only requires a limited volume of real-world images to fine-tune to a new domain.

© Repli5 AB. All rights reserved.