Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

2024-12-18 · Hanzhe Liang, Guoyang Xie, Chengbin Hou, Bingshu Wang, Can Gao, Jinbao Wang

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception~(ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine~(SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 3.2\% and 13.1\%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks.

📄 PDF Abstract BibTeX arXiv:2412.13461

Code (1)

M-3LAB/Look-Inside-for-More 공식 구현 pytorch

Tasks

3D Anomaly Detection Anomaly Detection

Methods 이 논문이 사용한 방법론

Focus 설명 없음

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

A Study on Trees's Knots Prediction from their Bark Outer-Shape

2020-10-05 · Mejri Mohamed, Antoine Richard, Cedric Pradalier

In the industry, the value of wood-logs strongly depends on their internal structure and more specifically on the knots' distribution inside the trees. As of today, CT-scanners are the prevalent tool to acquire accurate …

TabPFN Through The Looking Glass: An interpretability study of TabPFN and its internal representations

2026-01-13 · Aviral Gupta, Armaan Sethi, Dhruv Kumar arxiv

Tabular foundational models are pre-trained models designed for a wide range of tabular data tasks. They have shown strong performance across domains, yet their internal representations and learned concepts remain poorly…

A Survey On 3D Inner Structure Prediction from its Outer Shape

2020-02-11 · Mohamed Mejri, Antoine Richard, Cédric Pradalier

The analysis of the internal structure of trees is highly important for both forest experts, biological scientists, and the wood industry. Traditionally, CT-scanners are considered as the most efficient way to get an acc…

Multi-Modality Spatio-Temporal Forecasting via Self-Supervised Learning

2024-05-06 · Jiewen Deng, Renhe Jiang, JiaQi Zhang, Xuan Song

Multi-modality spatio-temporal (MoST) data extends spatio-temporal (ST) data by incorporating multiple modalities, which is prevalent in monitoring systems, encompassing diverse traffic demands and air quality assessment…

Self-Supervised Learning Spatio-Temporal Forecasting

LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives

2022-03-02 · Danial Maleki, H. R Tizhoosh

The volume of available data has grown dramatically in recent years in many applications. Furthermore, the age of networks that used multiple modalities separately has practically ended. Therefore, enabling bidirectional…

Cross-Modal Information Retrieval Cross-Modal Retrieval Information Retrieval Retrieval