← Depth Anomaly Detection and Segmentation

Papers with Code · CC BY-SA 4.0

MVTEC 3D-AD

아카이브 평가 13건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
TransFusion	Segmentation AUPRO 0.947 Detection AUROC 0.957	TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection 2023-11-16	코드 1
CPMF (2D+3D)	Segmentation AUPRO 0.9293 Detection AUROC 0.9515 Segmentation AUROC 0.9781	Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection 2023-03-23	코드 1 · 코드 2
CPMF (3D)	Segmentation AUPRO 0.9230 Detection AUROC 0.8304 Segmentation AUROC 0.9780	Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection 2023-03-23	코드 1 · 코드 2
CPMF (2D)	Segmentation AUPRO 0.9145 Detection AUROC 0.8918 Segmentation AUROC 0.9730	Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection 2023-03-23	코드 1 · 코드 2
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (SIFT)	Segmentation AUPRO 0.910 Detection AUROC 0.727 Segmentation AUROC 0.974	Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 2022-03-10	코드 1
3DSR (3D)	Segmentation AUPRO 0.907 Detection AUROC 0.922	Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation 2023-11-02	코드 1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (HoG)	Segmentation AUPRO 0.771 Detection AUROC 0.559 Segmentation AUROC 0.930	Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 2022-03-10	코드 1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (Depth iNet)	Segmentation AUPRO 0.755 Detection AUROC 0.675 Segmentation AUROC 0.930	Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 2022-03-10	코드 1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (NSA)	Segmentation AUPRO 0.5572 Detection AUROC 0.696 Segmentation AUROC 0.817	Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 2022-03-10	코드 1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (RaW)	Segmentation AUPRO 0.442 Detection AUROC 0.573 Segmentation AUROC 0.771	Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 2022-03-10	코드 1
Depth VM	Segmentation AUPRO 0.374 Detection AUROC 0.546	The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization 2021-12-16	코드 1 · 코드 2
Depth AE	Segmentation AUPRO 0.203 Detection AUROC 0.546	The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization 2021-12-16	코드 1 · 코드 2
Depth GAN	Segmentation AUPRO 0.143 Detection AUROC 0.523	The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization 2021-12-16	코드 1 · 코드 2