Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering

TL;DR

This survey comprehensively reviews the current state of 3D Scene Question Answering, highlighting datasets, methodologies, evaluation metrics, and future research directions to advance intelligent understanding of 3D environments.

Contribution

It provides the first systematic review of 3D SQA, organizing existing work and identifying shared patterns, limitations, and future research opportunities.

Findings

Shared architectural patterns identified across methods

Current trends like instruction tuning and zero-shot methods discussed

Challenges in dataset standardization and evaluation highlighted

Abstract

3D Scene Question Answering (3D SQA) represents an interdisciplinary task that integrates 3D visual perception and natural language processing, empowering intelligent agents to comprehend and interact with complex 3D environments. Recent advances in large multimodal modelling have driven the creation of diverse datasets and spurred the development of instruction-tuning and zero-shot methods for 3D SQA. However, this rapid progress introduces challenges, particularly in achieving unified analysis and comparison across datasets and baselines. In this survey, we provide the first comprehensive and systematic review of 3D SQA. We organize existing work from three perspectives: datasets, methodologies, and evaluation metrics. Beyond basic categorization, we identify shared architectural patterns across methods. Our survey further synthesizes core limitations and discusses how current trends, such as instruction tuning, multimodal alignment, and zero-shot, can shape future developments. Finally, we propose a range of promising research directions covering dataset construction, task generalization, interaction modeling, and unified evaluation protocols. This work aims to serve as a foundation for future research and foster progress toward more generalizable and intelligent 3D SQA systems.