Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
G-MAD is an innovative open-source framework that leverages the Arma3 game engine to generate synchronized multi-view RGB-T data specifically for aerial object detection. By addressing critical challenges in real-world dataset construction—such as viewpoint control, RGB-T alignment, and annotation costs—G-MAD enables structured scenario specification and automatic bounding box annotation through engine-level geometric metadata. The framework not only facilitates controlled studies in viewpoint variation and multi-modal fusion but also introduces the AMOD benchmark, a large-scale dataset for advancing aerial object detection research.
G-MAD revolutionizes aerial object detection by enabling precise control over multi-view data generation, overcoming traditional dataset limitations.
This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD addresses key limitations of real-world aerial dataset construction, including limited viewpoint control, imperfect RGB-T alignment and high annotation cost. The framework supports structured scenario specification, controllable multi-view camera placement, simultaneous visible/thermal capture, and automatic bounding box annotation using engine-level geometric metadata. These capabilities enable controlled studies of viewpoint variation, multi-modal fusion, and synthetic-to-real transfer in aerial object detection. Besides, using G-MAD, we construct and release AMOD, a new large-scale multi-view aerial RGB-T object detection benchmark. The source code and the dataset are available at https://unique-chan.github.io/G-MAD-Project.