LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving
This addresses the data augmentation challenge for autonomous driving systems, though it is incremental as it applies existing GAN methods to a specific sensor modeling task.
The paper tackled the problem of expensive and unsafe real data collection for autonomous driving by using CycleGANs to learn LiDAR sensor models from unpaired data, enabling realistic LiDAR generation from simulated data (sim2real) and high-resolution from low-resolution data (real2real), with experimental results showing high potential.
In the autonomous driving domain, data collection and annotation from real vehicles are expensive and sometimes unsafe. Simulators are often used for data augmentation, which requires realistic sensor models that are hard to formulate and model in closed forms. Instead, sensors models can be learned from real data. The main challenge is the absence of paired data set, which makes traditional supervised learning techniques not suitable. In this work, we formulate the problem as image translation from unpaired data and employ CycleGANs to solve the sensor modeling problem for LiDAR, to produce realistic LiDAR from simulated LiDAR (sim2real). Further, we generate high-resolution, realistic LiDAR from lower resolution one (real2real). The LiDAR 3D point cloud is processed in Bird-eye View and Polar 2D representations. The experimental results show a high potential of the proposed approach.