SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
This addresses the scalability and realism issues in sensor simulation for autonomous driving development, though it is incremental as it builds on existing surfel and GAN techniques.
The paper tackles the problem of generating realistic sensor data for autonomous driving simulations by proposing a method that uses texture-mapped surfels and a SurfelGAN network to synthesize camera images from limited lidar and camera data, demonstrating its effectiveness on the Waymo Open Dataset and a novel dataset with two vehicles observing the same scene.
Autonomous driving system development is critically dependent on the ability to replay complex and diverse traffic scenarios in simulation. In such scenarios, the ability to accurately simulate the vehicle sensors such as cameras, lidar or radar is essential. However, current sensor simulators leverage gaming engines such as Unreal or Unity, requiring manual creation of environments, objects and material properties. Such approaches have limited scalability and fail to produce realistic approximations of camera, lidar, and radar data without significant additional work. In this paper, we present a simple yet effective approach to generate realistic scenario sensor data, based only on a limited amount of lidar and camera data collected by an autonomous vehicle. Our approach uses texture-mapped surfels to efficiently reconstruct the scene from an initial vehicle pass or set of passes, preserving rich information about object 3D geometry and appearance, as well as the scene conditions. We then leverage a SurfelGAN network to reconstruct realistic camera images for novel positions and orientations of the self-driving vehicle and moving objects in the scene. We demonstrate our approach on the Waymo Open Dataset and show that it can synthesize realistic camera data for simulated scenarios. We also create a novel dataset that contains cases in which two self-driving vehicles observe the same scene at the same time. We use this dataset to provide additional evaluation and demonstrate the usefulness of our SurfelGAN model.