DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples

TL;DR

DMP-3DAD introduces a training-free, multi-view depth map projection method leveraging CLIP for cross-category 3D anomaly detection with few normal samples, achieving state-of-the-art results.

Contribution

The paper presents a novel, training-free framework using realistic depth map projection and CLIP for effective cross-category 3D anomaly detection in few-shot scenarios.

Findings

Achieves state-of-the-art performance on ShapeNetPart dataset.

Does not require fine-tuning or category-specific training.

Effective in practical few-shot cross-category anomaly detection.

Abstract

Cross-category anomaly detection for 3D point clouds aims to determine whether an unseen object belongs to a target category using only a few normal examples. Most existing methods rely on category-specific training, which limits their flexibility in few-shot scenarios. In this paper, we propose DMP-3DAD, a training-free framework for cross-category 3D anomaly detection based on multi-view realistic depth map projection. Specifically, by converting point clouds into a fixed set of realistic depth images, our method leverages a frozen CLIP visual encoder to extract multi-view representations and performs anomaly detection via weighted feature similarity, which does not require any fine-tuning or category-dependent adaptation. Extensive experiments on the ShapeNetPart dataset demonstrate that DMP-3DAD achieves state-of-the-art performance under few-shot setting. The results show that the proposed approach provides a simple yet effective solution for practical cross-category 3D anomaly detection.