RS-Paper-Hub — UAV Papershttps://rspaper.top/output/feed_uav.xml2026-04-20T10:19:45ZLatest remote sensing papers (last 7 days) — 1 entriesRS-Paper-Hubhttps://rspaper.topPixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentationhttp://arxiv.org/abs/2604.15670v12026-04-17T00:00:00Z2026-04-17T00:00:00ZShuyan KeYifan MeiChangli WuYonghan ZhengJiayi JiLiujuan CaoRongrong JiReasoning 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.<p><strong>Publication:</strong> CVPR 2026</p>
<p><strong>Category:</strong> Method</p>