Paper Detail
Yechan Kim, JongHyun Park, Dongho Yoon, Namhoon Jung, Moongu Jeon
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{kim2026g,
title = {G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection},
author = {Yechan Kim and JongHyun Park and Dongho Yoon and Namhoon Jung and Moongu Jeon},
year = {2026},
abstract = {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-le},
url = {https://huggingface.co/papers/2607.19942},
keywords = {code available, huggingface daily},
eprint = {2607.19942},
archiveprefix = {arXiv},
}
{}