Transformer-based Spatial Grounding: A Comprehensive Survey

TL;DR

This survey comprehensively reviews transformer-based spatial grounding methods, analyzing their architectures, datasets, and evaluation metrics to guide future research and industrial applications in associating language with image regions.

Contribution

It provides the first systematic synthesis of transformer-based spatial grounding approaches, highlighting trends, best practices, and practical insights from 2018 to 2025.

Findings

Identified dominant model architectures and datasets.

Analyzed evaluation metrics and methodological trends.

Provided guidance for industry-ready spatial grounding models.

Abstract

Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and cross-modal alignment. Despite this progress, the field lacks a comprehensive synthesis of current methodologies, dataset usage, evaluation metrics, and industrial applicability. This paper presents a systematic literature review of transformer-based spatial grounding approaches from 2018 to 2025. Our analysis identifies dominant model architectures, prevalent datasets, and widely adopted evaluation metrics, alongside highlighting key methodological trends and best practices. This study provides essential insights and structured guidance for researchers and practitioners, facilitating the development of robust, reliable, and industry-ready transformer-based spatial grounding models.