UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception
This addresses data scarcity for UAV imaging applications, though it is incremental as it adapts existing neural rendering methods to a specific domain.
The paper tackles the lack of diverse data for UAV-based perception by using neural rendering to generate synthetic images, showing that hybrid real-synthetic datasets boost detection model performance by a considerable margin.
Tremendous variations coupled with large degrees of freedom in UAV-based imaging conditions lead to a significant lack of data in adequately learning UAV-based perception models. Using various synthetic renderers in conjunction with perception models is prevalent to create synthetic data to augment the learning in the ground-based imaging domain. However, severe challenges in the austere UAV-based domain require distinctive solutions to image synthesis for data augmentation. In this work, we leverage recent advancements in neural rendering to improve static and dynamic novelview UAV-based image synthesis, especially from high altitudes, capturing salient scene attributes. Finally, we demonstrate a considerable performance boost is achieved when a state-ofthe-art detection model is optimized primarily on hybrid sets of real and synthetic data instead of the real or synthetic data separately.