Solar Altitude Guided Scene Illumination
This work addresses the problem of limited real-world data for autonomous driving by providing a method to generate varied daytime scenes, though it is incremental in focusing on a specific conditioning aspect.
The paper tackles the challenge of generating synthetic daytime camera sensor data for autonomous driving by introducing solar altitude as a global conditioning variable, which eliminates manual labeling and captures lighting and noise variations effectively.
The development of safe and robust autonomous driving functions is heavily dependent on large-scale, high-quality sensor data. However, real-world data acquisition requires extensive human labor and is strongly limited by factors such as labeling cost, driver safety protocols and scenario coverage. Thus, multiple lines of work focus on the conditional generation of synthetic camera sensor data. We identify a significant gap in research regarding daytime variation, presumably caused by the scarcity of available labels. Consequently, we present solar altitude as global conditioning variable. It is readily computable from latitude-longitude coordinates and local time, eliminating the need for manual labeling. Our work is complemented by a tailored normalization approach, targeting the sensitivity of daylight towards small numeric changes in altitude. We demonstrate its ability to accurately capture lighting characteristics and illumination-dependent image noise in the context of diffusion models.