cs.CVNov 12, 2026

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

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

Organizations: Hohai University · Key Laboratory of Water Big Data Technology of Ministry of Water Resources

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

Figures & tables

Explore similar work

CardsList
  1. Fly360: Omnidirectional Obstacle Avoidance within Drone View

    Mar 6, 2026Xiangkai Zhang, Dizhe Zhang, WenZhuo Cao +5UAV NavigationRobot Collision Avoidance

  2. OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation

    Oct 29, 2026Junli Liu, Zhongrui You, Chenhui Li +9Aerial VLNVision-Language-Action Models

  3. SkyShield: Occupancy as a Safety Interface for Low-Altitude UAV Autonomy

    May 30, 2026Jie Gao, Jie Ma, Kaihui Lin +4Aerial RoboticsUAV Navigation