Bootstrapping Corner Cases: High-Resolution Inpainting for Safety Critical Detect and Avoid for Automated Flying
In autonomous UAV flight, Detect-and-Avoid (DAA) systems suffer from severe scarcity of real-world airspace data—particularly annotated corner cases such as small-scale or head-on approaching objects. To address this, we propose a geometry-aware conditional diffusion model for high-fidelity image inpainting, integrating sensor constraints and flight dynamic priors to synthesize physically plausible, pixel-accurately annotated corner-case samples. Our method overcomes traditional data collection bottlenecks and enables few-shot-driven data augmentation. Based on it, we construct the first publicly available high-resolution DAA corner-case dataset. Experiments demonstrate that detectors trained solely on real data achieve a 37.2% improvement in recall and a 51.8% reduction in false positives on challenging corner cases when augmented with our synthetic samples.