Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

TL;DR

Structured Domain Randomization (SDR) improves synthetic data generation by incorporating scene context, leading to better neural network performance in 2D object detection tasks and bridging the reality gap effectively.

Contribution

SDR introduces context-aware scene structuring in synthetic data generation, outperforming traditional domain randomization methods in object detection accuracy.

Findings

SDR achieves competitive results on real data after training solely on synthetic images.

SDR outperforms other synthetic data generation methods like VKITTI and Sim 200k.

Combining SDR synthetic data with real data enhances detection performance beyond using real data alone.

Abstract

We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.