arXiv cs.AI· Rugved Katole, Vedant Patil, Jenna Kline, Christopher Stewart·· 1 天前AI 评分38
梦境比飞行更便宜：精选世界模型数据提升空中检测性能
Dreams Are Cheaper Than Flights: Curated World-Model Data Improves Aerial Detection
AI 导读
用野生动物无人机视频为 7B 参数世界模型播种，精选生成帧可将训练集扩充一倍以上；在同款无人机的留出视频上，这些帧加入真实数据使 mAP@50--95 提升 4.3%，替换真实数据提升 10.3%，在城市基准上最高提升 33.5%。
正文 · 原文
Abstract:Robot perception is increasingly data driven, yet field data is slow, costly, and sometimes disruptive to collect. Video world models offer a cheaper source: seeded with real frames, they extend a recorded scene into new footage with the deployment's sensor, altitude, and environment. We ask whether such synthetic data matches the utility of real field data and whether detectors trained with it perform in the field. Seeding a 7B-parameter world model with wildlife drone video, we more than double the training set with curated frames. On held-out videos from the same drones, mAP@50--95 rises 4.3\% when these frames are added to real data and 10.3\% when they replace it, and up to 33.5\% on an urban benchmark. Although an expert rejects an estimated 87.5\% of generated clips, the data costs about \$1,100 of GPU time, against more than \$3,200 of field labor alone for a less useful real training set. Synthetic data thus shifts data costs from fieldwork to compute.
| Comments: | 6 pages, Corl 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41030 [cs.CV] |
| (or arXiv:2610.41030v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41030 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rugved Katole [view email]
[v1]
Thu, 29 Oct 2026 22:17:32 UTC (148 KB)
来源：arXiv cs.AI · arxiv.org