SyncAI.news, a Varaisys broadcasting
AerialOcc: Unified 3D Aerial Perception without Task-Specific Head
FL

Fan Liu, Xiang Gu, Baoyu Lv, Chuanyi Zhang, Liang Yao, Yuye Ma, Yuhui Zheng

· 1 min read

ResearcharXiv cs.CV

AerialOcc: Unified 3D Aerial Perception without Task-Specific Head

arXiv:2611.18770v1 Announce Type: new Abstract: Aerial perception systems are increasingly expected to support diverse tasks, yet existing solutions remain fundamentally tied to task-specific outputs. Detection, segmentation, and other perception objectives are usually learned either by separate models or by sharing a backbone with multiple task heads, leaving the model itself unaware of the common structure underlying these tasks. We are interested in asking: can a single perception representation support different levels of understanding without being designed for any specific task? We notice that occupancy is a promising task-agnostic representation for drone perception. By modeling the spatial existence and semantics of the environment, it naturally bridges different perception granularities, from coarse scene understanding to fine-grained object localization. Therefore, we introduce AerialOcc, a unified occupancy-based perception model that enables multiple drone perception tasks from a single inference process, without maintaining task-specific prediction heads. To facilitate this direction, we construct AerialOcc-20K, a large-scale multi-class occupancy dataset for aerial environments. Extensive experiments show that AerialOcc achieves competitive performance across diverse perception tasks while preserving a unified architecture. Our findings demonstrate that occupancy can serve as a universal perception interface, offering a new perspective toward flexible and scalable visual intelligence for autonomous drones from a common 3D scene representation. Models and data are publicly available at https://github.com/guxiang2002/AerialOcc

Original source

This story was published by arXiv cs.CV and written by Fan Liu, Xiang Gu, Baoyu Lv, Chuanyi Zhang, Liang Yao, Yuye Ma, Yuhui Zheng. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News