arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.01100cs.CVcs.AI
收藏

Fence定理:面向3D异常检测预处理阶段的双目标语义-结构隔离

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机与软件学院);Shenzhen Audencia Financial Technology Institute, Shenzhen University(深圳大学深圳 Audencia 金融科技研究院);National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University(深圳大学大数据系统计算技术国家工程实验室);Faculty of Education, Shenzhen University(深圳大学教育学院);Guangdong Provincial Key Laboratory of Intelligent Information Processing(广东省智能信息处理重点实验室)

Hanzhe Liang, Jie Zhou, Xuanxin Chen, Tao Dai, Jinbao Wang, Can Gao

AI总结:

本文提出Fence定理,将3D异常检测预处理形式化为双目标语义隔离器,并基于此实现Patch3D方法,通过细粒度语义对齐显著提升点级异常检测准确率。

摘要:

3D异常检测(AD)虽然重要,但由于缺乏用于预处理设计的统一理论基础而十分困难。我们建立了Fence定理,将预处理形式化为双目标语义隔离器:(1)在可行范围内最大程度地减轻跨语义干扰,以及(2)在可行的地方将异常判断限制在已对齐的语义空间内,从而建立语义内的可比性。任何预处理方法都通过Emantic-Division和Spatial-Constraints阶段的两阶段过程来实现这一目标。通过系统解构,我们基于定性分析、定量研究和数学证明这三方证据,在理论和实验上将现有的预处理方法统摄于该定理之下。在Fence定理的指导下,我们实现了Patch3D,它由Patch-Cutting和Patch-Matching模块组成,用于分割语义空间并合并相似空间,同时在每个空间内独立建模正常特征。在Anomaly-ShapeNet和Real3D-AD上不同设置下的实验表明,预处理中逐步细化的语义对齐直接提升了点级AD的准确率,为该定理的因果逻辑提供了逆向验证。

英文摘要:

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgments to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Emantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem's causal logic.

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。

↑