PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
This work provides the first formal definition and benchmark for reasoning segmentation in UAV imagery, enabling future research in this domain.
The paper defines the UAV Reasoning Segmentation task and constructs DRSeg, a benchmark with 10k high-resolution aerial images and Chain-of-Thought QA supervision. It introduces PixDLM, a multimodal language model baseline, achieving strong results and highlighting UAV-specific challenges.
Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these issues, we formally define the UAV Reasoning Segmentation task and organize its semantic requirements into three dimensions: Spatial, Attribute, and Scene-level reasoning. Based on this formulation, we construct DRSeg, a large-scale benchmark for UAV reasoning segmentation, containing 10k high-resolution aerial images paired with Chain-of-Thought QA supervision across all three reasoning types. As a benchmark companion, we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task. Experiments on DRSeg establish strong baseline results and highlight the unique challenges of UAV reasoning segmentation, providing a solid foundation for future research.