Semantic Road Layout Understanding by Generative Adversarial Inpainting
This work addresses scene comprehension for autonomous vehicles, but it is incremental as it builds on existing GAN and inpainting techniques.
The paper tackled the problem of understanding static road layouts for autonomous driving by using a GAN-based semantic segmentation inpainting model to remove dynamic objects from scenes, achieving evaluation on Cityscapes and a new synthetic dataset from CARLA simulator with comparisons to baselines in RGB and segmentation domains.
Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in. The ability to discern static environment and dynamic entities provides a comprehension of the road layout that poses constraints to the reasoning process about moving objects. We pursue this through a GAN-based semantic segmentation inpainting model to remove all dynamic objects from the scene and focus on understanding its static components such as streets, sidewalks and buildings. We evaluate this task on the Cityscapes dataset and on a novel synthetically generated dataset obtained with the CARLA simulator and specifically designed to quantitatively evaluate semantic segmentation inpaintings. We compare our methods with a variety of baselines working both in the RGB and segmentation domains.