SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jiaxin, Li, Ziwen, Zhang, Hanlve, Chen, Runnan, He, Xiao, Guo, Yandong, Wang, Wenping, Liu, Tongliang, Gong, Mingming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918088325201920
author Huang, Jiaxin
Li, Ziwen
Zhang, Hanlve
Chen, Runnan
He, Xiao
Guo, Yandong
Wang, Wenping
Liu, Tongliang
Gong, Mingming
author_facet Huang, Jiaxin
Li, Ziwen
Zhang, Hanlve
Chen, Runnan
He, Xiao
Guo, Yandong
Wang, Wenping
Liu, Tongliang
Gong, Mingming
contents The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between objects, remains underexplored in current 3D vision-language research. Existing datasets often mix semantic cues (e.g., object name) with spatial context, leading models to rely on superficial shortcuts rather than genuinely interpreting spatial relationships. To address this gap, we introduce S\textsc{urprise}3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes. S\textsc{urprise}3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2, including more than 2.8k unique object classes. The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name, thereby mitigating shortcut biases in spatial understanding. These queries comprehensively cover various spatial reasoning skills, such as relative position, narrative perspective, parametric perspective, and absolute distance reasoning. Initial benchmarks demonstrate significant challenges for current state-of-the-art expert 3D visual grounding methods and 3D-LLMs, underscoring the necessity of our dataset and the accompanying 3D Spatial Reasoning Segmentation (3D-SRS) benchmark suite. S\textsc{urprise}3D and 3D-SRS aim to facilitate advancements in spatially aware AI, paving the way for effective embodied interaction and robotic planning. The code and datasets can be found in https://github.com/liziwennba/SUPRISE.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
Huang, Jiaxin
Li, Ziwen
Zhang, Hanlve
Chen, Runnan
He, Xiao
Guo, Yandong
Wang, Wenping
Liu, Tongliang
Gong, Mingming
Computer Vision and Pattern Recognition
Robotics
The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between objects, remains underexplored in current 3D vision-language research. Existing datasets often mix semantic cues (e.g., object name) with spatial context, leading models to rely on superficial shortcuts rather than genuinely interpreting spatial relationships. To address this gap, we introduce S\textsc{urprise}3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes. S\textsc{urprise}3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2, including more than 2.8k unique object classes. The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name, thereby mitigating shortcut biases in spatial understanding. These queries comprehensively cover various spatial reasoning skills, such as relative position, narrative perspective, parametric perspective, and absolute distance reasoning. Initial benchmarks demonstrate significant challenges for current state-of-the-art expert 3D visual grounding methods and 3D-LLMs, underscoring the necessity of our dataset and the accompanying 3D Spatial Reasoning Segmentation (3D-SRS) benchmark suite. S\textsc{urprise}3D and 3D-SRS aim to facilitate advancements in spatially aware AI, paving the way for effective embodied interaction and robotic planning. The code and datasets can be found in https://github.com/liziwennba/SUPRISE.
title SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2507.07781