3D Question Answering for City Scene Understanding
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2156-2165
Abstract
3D multimodal question answering (MQA) plays a crucial role in scene understanding by enabling intelligent agents to comprehend their surroundings in 3D environments. While existing research has primarily focused on indoor household tasks and outdoor roadside autonomous driving tasks, there has been limited exploration of city-level scene understanding tasks. Furthermore, existing research faces challenges in understanding city scenes, due to the absence of spatial semantic information and human-environment interaction information at the city level.To address these challenges, we investigate 3D MQA from both dataset and method perspectives. From the dataset perspective, we introduce a novel 3D MQA dataset named City-3DQA for city-level scene understanding, which is the first dataset to incorporate scene semantic and human-environment interactive tasks within the city. From the method perspective, we propose a Scene graph enhanced City-level Understanding method (Sg-CityU), which utilizes the scene graph to introduce the spatial semantic. A new benchmark is reported and our proposed Sg-CityU achieves accuracy of 63.94 % and 63.76 % in different settings of City-3DQA. Compared to indoor 3D MQA methods and zero-shot using advanced large language models (LLMs), Sg-CityU demonstrates state-of-the-art (SOTA) performance in robustness and generalization.Keywords
All Related Versions
Funding Information
- Hong Kong RIF (Grant No. R6021-20)
- the Postdoctoral Fellowship Program of CPSF (Grant Number GZC20232292)
- Hong Kong CRF (Grant No. C2004-21G and C7004-22G)
This publication has 29 references indexed in Scilit:
- Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset2022
- Point Scene Understanding via Disentangled Instance Mesh Reconstruction2022
- 3DVQA: Visual Question Answering for 3D Environments2022
- SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point CloudsInternational Journal of Computer Vision, 2022
- A global horizon scan of the future impacts of robotics and autonomous systems on urban ecosystemsNature Ecology & Evolution, 2021
- Embodied Question Answering in Photorealistic Environments With Point Cloud Perception2019
- Multi-Target Embodied Question Answering2019
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Tackling Global Grand Challenges in Our CitiesEngineering, 2016
- Synonyms provide semantic preview benefit in EnglishJournal of Memory and Language, 2013