English(EN) Can One Hear Geometry? Gauge-Invariant Spectral Descriptors for Text-to-B-rep Retrieval

新方法使用谱不变量进行精确的3D实体检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了一种新颖的文本到3D实体检索框架，该框架利用群作用和谱几何不变量。该方法明确约束描述符的构建，以确保对姿态、尺度和记录约定等变换的不变性，解决了现有方法离散化 B-rep 模型或在没有明确不变性保证的情况下学习特征的局限性。所提出的方法在文本到3D实体检索任务上实现了 88.6% 的 Recall@5，比之前的最先进水平提高了 13.6 个百分点。 AI

影响这项研究通过提高几何精度和不变性，推动了文本到3D检索的发展，有望增强3D内容创建和搜索领域的应用。

排序理由该集群包含一篇详细介绍3D实体检索新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍3D实体检索新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Hongzhu Yi, Hao Liu, Tao Yu, Tiankun Yang, Yujia Yang, Zhenghao Zhang, Tianyu Zong, Zhenyu Guan, Bingkang Shi, Haopeng Jin, Yuanxiang Wang, Zhongtian Luo, Jungang Xu · 2026-10-27 04:00

能否听见几何？用于文本到B-rep检索的规范不变谱描述符

arXiv:2610.33484v1 Announce Type: new Abstract: Text-to-3D solid retrieval requires aligning natural language with precise geometry despite variations in pose, scale, and recording conventions. Existing methods discretize Boundary Representation (B-rep) models into point clouds o…

本文如何被排名

报道来源 [1]

能否听见几何？用于文本到B-rep检索的规范不变谱描述符

相关实体

相关话题