SURPRISE3D：面向复杂3D场景空间理解与推理的数据集
SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
AI总结：
针对3D视觉-语言研究中空间关系被语义线索干扰的问题，提出SURPRISE3D数据集及3D-SRS基准，通过无物体名称的89k+空间查询评估复杂场景下的空间推理分割，推动具身AI与机器人规划发展。
摘要：
语言与3D感知的整合对于具身AI和机器人系统感知、理解并与物理世界交互至关重要。空间推理作为理解物体间空间关系的关键能力，在当前的3D视觉-语言研究中仍处于未被充分探索的状态。现有数据集常将语义线索（如物体名称）与空间上下文混合，导致模型依赖表面捷径而非真正解读空间关系。为填补此空白，我们提出SURPRISE3D，一个旨在评估复杂3D场景中语言引导空间推理分割的新颖数据集。SURPRISE3D包含来自ScanNet++ v2的900多个精细室内场景中超过200k视觉-语言对，涵盖超过2.8k独特物体类别。该数据集包含89k+条人工标注的空间查询，这些查询在构建时刻意不包含物体名称，从而缓解空间理解中的捷径偏差。这些查询全面覆盖多种空间推理技能，如相对位置、叙述视角、参数视角和绝对距离推理。初始基准测试表明，当前最先进的专家级3D视觉定位方法和3D-LLMs面临重大挑战，凸显了本数据集及配套的3D空间推理分割（3D-SRS）基准套件的必要性。SURPRISE3D和3D-SRS旨在推动空间感知AI的发展，为有效的具身交互与机器人规划铺平道路。代码和数据可在https://github.com/liziwennba/SUPRISE获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
