10000+高质量3D资产，开箱即用，适配机器人与空间计算
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
- 合成10000+带度量尺度、确定锚点的3D资产，支持零样本部署
- 在Habitat-Sim中99.1%物理稳定，推理速度提升20倍，无重叠场景
- 提升3.4倍CLIP召回率，适合需高精度3D环境的智能体研究
网络规模的3D资产虽丰富，但常因度量尺度混乱、中心点错误、几何脆弱和纹理缺失，难以用于具身AI、机器人和空间计算。我们提出AmaraSpatial-10K，包含超10000个合成3D资产，均以度量尺度对齐、确定锚点的.glb格式提供，分离了PBR贴图、凸碰撞外壳、参考图像及多句文本元数据。配套构建评估套件，包括连续尺度合理性得分（SPS）、LLM概念密度指标、锚点误差审计和跨模态CLIP一致性协议，并应用于AmaraSpatial-10K及匹配的Objaverse、HSSD、ABO、GSO子集。结果表明，其在CLIP Recall@5上较Objaverse提升3.4倍（0.612 vs. 0.181），中位排名从267降至3；在Habitat-Sim中实现99.1%物理稳定性，约20倍加速；作为Holodeck的直接资产库时可生成零重叠场景。控制消融实验表明检索性能提升源于描述丰富性。
原文摘要 · Abstract (English)
Web-scale 3D asset collections are abundant but rarely deployment-ready, suffering from arbitrary metric scaling, incorrect pivots, brittle geometry, and incomplete textures, defects that limit their use in embodied AI, robotics, and spatial computing. We present AmaraSpatial-10K, a dataset of over 10,000 synthetic 3D assets optimised for zero-shot deployment. Each asset ships as a metric-scaled, deterministically anchored .glb with separated PBR maps, a convex collision hull, a paired reference image, and multi-sentence text metadata. Alongside the dataset we introduce a reusable evaluation suite for 3D asset banks, a continuous Scale Plausibility Score (SPS), an LLM Concept Density metric, anchor-error auditing, and a cross-modal CLIP coherence protocol, and apply it to AmaraSpatial-10K alongside matched subsets of Objaverse, HSSD, ABO, and GSO. AmaraSpatial-10K improves CLIP Recall@5 by $3.4\times$ over Objaverse ($0.612$ vs. $0.181$, median rank $267 \rightarrow 3$), achieves a $99.1\%$ physics-stability rate under Habitat-Sim with $\sim 20\times$ wall-time speed-up, and produces zero-overlap scenes when used as a drop-in asset bank for Holodeck. Controlled ablations on the same asset bank attribute the retrieval gain to description richness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。