arXiv cs.AI· Yanbo Wang, Siqi Luo, Siyu Zhang, Chenming Zhu, Wenzhao Zheng, Qian Yu, Juncheng Yan, Bin Fu, Tai Wang, Yu Qiao, Yihao Liu, Jiwen Lu·· 12 小时前AI 评分32
MindView：生成式多视角空间智能基准发布
MindView: Benchmarking Generative Multi-View Spatial Intelligence
AI 导读
研究者推出 MindView 基准，用于评估生成式多视角空间智能，包含来自 513 个场景的 1,500 个样本和七项任务，分为几何主导与语义主导两类。对 11 个生成器的评测显示整体仍有较大提升空间，且在扩展上下文设置下所有模型总分均下降。
正文 · 原文
Authors:Yanbo Wang, Siqi Luo, Siyu Zhang, Chenming Zhu, Wenzhao Zheng, Qian Yu, Juncheng Yan, Bin Fu, Tai Wang, Yu Qiao, Yihao Liu, Jiwen Lu
Abstract:Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view observations remains underexplored. We introduce MindView, a benchmark for generative multi-view spatial intelligence with 1,500 samples from 513 scenes across three indoor datasets. Its seven tasks form two families: geometry-dominant tasks specify changes in camera position and orientation, while semantics-dominant tasks require inferring target viewpoints by grounding referred objects and interpreting spatial relations and reference-frame cues. Evaluation of eleven generators reveals substantial room for improvement on MindView. A paired context analysis further shows that all eleven generators obtain lower overall scores under the expanded context setting. These findings motivate us to investigate whether task-specific supervision can improve target-view generation and whether models can use additional multi-view evidence effectively. We therefore fine-tune BAGEL on the MindView training dataset, improving its overall score by 24.3 points and yielding gains across all seven MindView tasks. Beyond these generation gains, the fine-tuned model also yields higher scores on three spatial-understanding benchmarks without training on their annotations, suggesting that learning to generate spatially grounded views may benefit spatial understanding. To improve evidence utilization under expanded context, we propose MindCue, a training-free spatial evidence selector guided by a target-view hypothesis. MindCue reverses the drop in overall score under expanded context and outperforms the standard-context baseline. Overall, MindView provides a concrete testbed for generative multi-view spatial intelligence.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28622 [cs.CV] |
| (or arXiv:2610.28622v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28622 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanbo Wang [view email]
[v1]
Tue, 20 Oct 2026 17:58:25 UTC (10,925 KB)
来源：arXiv cs.AI · arxiv.org