MOO：用于牛只重识别视角分析的多视角定向观测数据集

View PDF HTML (experimental)

Abstract:Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at this https URL.

Comments:	31 pages, 10 figures, extended version of the paper accepted to the CVPR 2026 Workshop on Computer Vision for Animal Behavior Tracking and Modeling (CV4Animals)
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2603.04314 [cs.CV]
	(or arXiv:2603.04314v3 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2603.04314 arXiv-issued DOI via DataCite

Submission history

From: William Grolleau [view email]
[v1] Wed, 4 Mar 2026 17:36:26 UTC (5,160 KB)
[v2] Thu, 28 May 2026 15:13:29 UTC (5,161 KB)
[v3] Thu, 5 Nov 2026 10:14:23 UTC (4,853 KB)