A Unified Framework and Dataset for Oriented Object Visual Grounding in Remote Sensing

2026-09-23

AI Summary

该研究解决了遥感图像中任意方向物体的视觉定位问题，通过引入O²-VG模型家族及DIOR-R-RSVG数据集，采用跨模态变换器和自回归视觉-语言模型方法。

Abstract

Visual grounding in remote sensing images aims to locate objects described by referring expressions. Most existing methods predict horizontal bounding boxes, which are often inaccurate for objects with arbitrary orientations. To address this limitation, we introduce O$^2$-VG, a family of models for oriented object visual grounding with three complementary designs. Specifically, O$^2$-VG-Trans is a cross-modality transformer for oriented object visual grounding. It establishes a strong discriminative foundation for the model family. Building upon it, O$^2$-VG-Uni predicts universal oriented proposals for possible foreground objects without specific text prompts. It also supports object retrieval through cached proposal embeddings. Using these universal oriented proposals as input prompts, O$^2$-VG-VLM is an autoregressive vision-language model. It generates oriented box token blocks in parallel through multi-token prediction. In addition, we construct DIOR-R-RSVG, a dataset for oriented object visual grounding in remote sensing images. It provides image, expression, and oriented box triplets for training and evaluation. Together, the O$^2$-VG family provides a flexible framework that spans discriminative transformers and generative vision-language models. It achieves superior performance across multiple benchmarks. Code is available at https://github.com/wokaikaixinxin/ai4rs.

Problem

• Visual Grounding
• Remote Sensing
• Oriented Objects

Innovation

• Oriented Object Visual Grounding
• Cross-modality Transformer
• Universal Oriented Proposals
• Autoregressive Vision-Language Model
• DIOR-R-RSVG Dataset