paper-with-me

Papers

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

2018-10-23 · Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, Stan Birchfield

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.

📄 PDF Abstract BibTeX arXiv:1810.10093

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Comparison of synthetic dataset generation methods for medical intervention rooms using medical clothing detection as an example

2022-09-23 · Patrick Schülein, Hannah Teufel, Ronja Vorpahl, Indira Emter 외

The availability of real data from areas with high privacy requirements, such as the medical intervention space, is low and the acquisition legally complex. Therefore, this work presents a way to create a synthetic datas…

Dataset GenerationMixed RealityUnity

Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning

2023-07-21 · Arthur Müller, Matthia Sabatelli

Reinforcement Learning (RL) has been widely explored in Traffic Signal Control (TSC) applications, however, still no such system has been deployed in practice. A key barrier to progress in this area is the reality gap, t…

Meta-LearningReinforcement Learning (RL)Traffic Signal Control

Synthetic Data Generation for Bridging Sim2Real Gap in a Production Environment

2023-11-18 · Parth Rawal, Mrunal Sompura, Wolfgang Hintze

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an impo…

6D Pose Estimation using RGBObjectobject-detectionObject Detection+3

Data-efficient Domain Randomization with Bayesian Optimization

2020-03-05 · Fabio Muratore, Christian Eilers, Michael Gienger, Jan Peters

When learning policies for robot control, the required real-world data is typically prohibitively expensive to acquire, so learning in simulation is a popular strategy. Unfortunately, such polices are often not transfera…

Bayesian Optimization

Bridging the Reality Gap for Pose Estimation Networks using Sensor-Based Domain Randomization

2020-11-17 · Frederik Hagelskjaer, Anders Glent Buch

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required fo…

Data AugmentationPose Estimation