Synth It Like KITTI: Synthetic Data Generation for Object Detection in Driving Scenarios
An important factor in advancing autonomous driving systems is simulation. Yet, there is rather small progress for transferability between the virtual and real world. We revisit this problem for 3D object detection on LiDAR point clouds and propose a dataset generation pipeline based on the CARLA simulator. Utilizing domain randomization strategies and careful modeling, we are able to train an object detector on the synthetic data and demonstrate strong generalization capabilities to the KITTI dataset. Furthermore, we compare different virtual sensor variants to gather insights, which sensor attributes can be responsible for the prevalent domain gap. Finally, fine-tuning with a small portion of real data almost matches the baseline and with the full training set slightly surpasses it.
Code (1)
Tasks
3D Object DetectionAutonomous DrivingDataset Generationobject-detectionObject DetectionSynthetic Data GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
KITTI-CARLA: a KITTI-like dataset generated by CARLA Simulator
KITTI-CARLA is a dataset built from the CARLA v0.9.10 simulator using a vehicle with sensors identical to the KITTI dataset. The vehicle thus has a Velodyne HDL64 LiDAR positioned in the middle of the roof and two color …
Semantic SegmentationTransfer LearningSynthetic Dataset Evaluation Based on Generalized Cross Validation
With the rapid advancement of synthetic dataset generation techniques, evaluating the quality of synthetic data has become a critical research focus. Robust evaluation not only drives innovations in data generation metho…
Transfer LearningTRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments
High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require intensive investments and yield low-divers…
DiversitySemantic SegmentationSynthetic Data GenerationStructured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
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 ac…
Self-Supervised Real-to-Sim Scene Generation
Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can its…
Graph GenerationScene GenerationScene Graph GenerationSynthetic Data Generation+1