DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models

TL;DR

DVGBench introduces a new benchmark and LVLM model for implicit visual grounding in drone imagery, emphasizing scene-specific reasoning and converting implicit references into explicit ones to improve performance.

Contribution

The paper presents DVGBench, a high-quality implicit visual grounding dataset for drones, and DroneVG-R1, a novel LVLM with Implicit-to-Explicit Chain-of-Thought for improved reasoning.

Findings

Mainstream models struggle with implicit grounding tasks.

Scene-specific expertise enhances grounding accuracy.

Explicit and implicit task performance reveals reasoning limitations.

Abstract

Remote sensing (RS) large vision-language models (LVLMs) have shown strong promise across visual grounding (VG) tasks. However, existing RS VG datasets predominantly rely on explicit referring expressions-such as relative position, relative size, and color cues-thereby constraining performance on implicit VG tasks that require scenario-specific domain knowledge. This article introduces DVGBench, a high-quality implicit VG benchmark for drones, covering six major application scenarios: traffic, disaster, security, sport, social activity, and productive activity. Each object provides both explicit and implicit queries. Based on the dataset, we design DroneVG-R1, an LVLM that integrates the novel Implicit-to-Explicit Chain-of-Thought (I2E-CoT) within a reinforcement learning paradigm. This enables the model to take advantage of scene-specific expertise, converting implicit references into explicit ones and thus reducing grounding difficulty. Finally, an evaluation of mainstream models on both explicit and implicit VG tasks reveals substantial limitations in their reasoning capabilities. These findings provide actionable insights for advancing the reasoning capacity of LVLMs for drone-based agents. The code and datasets will be released at https://github.com/zytx121/DVGBench