paper-with-me

홈 › Papers

Synth It Like KITTI: Synthetic Data Generation for Object Detection in Driving Scenarios

2025-02-20 · Richard Marcus, Christian Vogel, Inga Jatzkowski, Niklas Knoop, Marc Stamminger

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.

📄 PDF Abstract BibTeX arXiv:2502.15076

Code (1)

richardmarcus/synth-it-like-kitti 공식 구현

Tasks

3D Object DetectionAutonomous DrivingDataset Generationobject-detectionObject DetectionSynthetic Data Generation

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
CARLA CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban…

Similar Papers 제목 키워드 기반

KITTI-CARLA: a KITTI-like dataset generated by CARLA Simulator

2021-08-17 · Jean-Emmanuel Deschaud

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 Learning

Synthetic Dataset Evaluation Based on Generalized Cross Validation

2025-09-14 · Zhihang Song, Dingyi Yao, Ruibo Ming, Lihui Peng 외 arxiv

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 Learning

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments

2022-08-16 · Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar

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 Generation

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

2018-10-23 · Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna 외

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

2020-11-30 · ICCV 2021 10 · Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci 외

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