跳到正文
arXiv cs.AI· Pooya Khosravi, Jen-Feng Chang, Fnu Pramono·· 10 小时前AI 评分31

SixthView:隐藏视图重建与 3D 装配推理基准

SixthView: A Benchmark for Hidden-View Reconstruction and 3D Assembly Reasoning

AI 导读

SixthView 是一个从五个正交视图预测第六视图的 3D 装配推理基准,含 602 个合成 polycube 装配体,零件数 2–10,要求对缺失视图输出密集零件标签网格。

正文 · 原文

View PDF HTML (experimental)

Abstract:Inferring the unseen side of a 3D assembly requires reasoning about part placement and occlusion. Different assemblies can match the observed views while producing different hidden views, leaving the target ambiguous. We introduce SixthView, a benchmark in which models predict a sixth orthographic view from five observed views and information about the component shapes. The benchmark contains 602 synthetic polycube assemblies with 2--10 parts and requires a dense grid of part labels for the missing view, allowing both exact-view and cell-level evaluation. For each item, we exhaustively verify that all legal assemblies consistent with the exact component geometry and observed label grids yield the same target view. With these inputs, the task tests symbolic assembly and coordinate reasoning. The image-only variants additionally require shape recovery from rendered views, where occlusion can make different 3D shapes look identical. We evaluate three vision-language models under four input conditions. Across 552 items with complete evaluations, exact-grid accuracy with images plus exact text ranges from 33.2% to 85.4%. Adding exact text to separate images improves accuracy by 19.7--63.0 percentage points, whereas adding images to exact text changes it by only $-0.5$ to $+2.1$ points. Separate image panels outperform a merged sheet by 6.7--11.1 points. The results show that performance depends strongly on access to exact symbolic information, with little further improvement from images once the geometry is specified. GitHub: this https URL
Comments: 13 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23891 [cs.CV]
  (or arXiv:2611.23891v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.23891

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jen-Feng Chang [view email]
[v1] Wed, 18 Nov 2026 05:42:33 UTC (2,449 KB)

来源:arXiv cs.AI · arxiv.org