Paper Detail

G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection

Yechan Kim, JongHyun Park, Dongho Yoon, Namhoon Jung, Moongu Jeon

huggingface Score 6.8

Published 2026-07-22 · First seen 2026-07-23

General AI

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-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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@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},
}

Metadata

{}