Shape-Guided Dual-Memory Learning for 3D Anomaly Detection
Jul 24, 2023
Sprecher:innen
Yu-Min Chu
Sprecher:in · 0 Follower:innen
Ting-I Hsieh
Sprecher:in · 0 Follower:innen
Hwann-Tzong Chen
Sprecher:in · 0 Follower:innen
Tyng-Luh Liu
Sprecher:in · 0 Follower:innen
Über
We present a shape-guided expert-learning framework to tackle the problem of unsupervised 3D anomaly detection. Our method is established on the effectiveness of two specialized expert models and their synergy to localize anomalous regions from color and shape modalities. The first expert utilizes geometric information to probe 3D structural anomalies by modeling the implicit distance fields around local shapes. The second expert considers the 2D RGB features associated with the first expert to identify color appearance irregularities on the local shapes. We use the two experts to build the dual memory banks from the anomaly-free training samples and perform shape-guided inference to pinpoint the defects in the testing samples. Owing to the per-point 3D representation and the effective fusion scheme of complementary modalities, our method efficiently achieves state-of-the-art performance on the MVTec 3D-AD dataset with better recall and lower false positive rates, as preferred in real applications.We present a shape-guided expert-learning framework to tackle the problem of unsupervised 3D anomaly detection. Our method is established on the effectiveness of two specialized expert models and their synergy to localize anomalous regions from color and shape modalities. The first expert utilizes geometric information to probe 3D structural anomalies by modeling the implicit distance fields around local shapes. The second expert considers the 2D RGB features associated with the first expert to…
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Understanding the Role of Feedback in Online Learning with Switching Costs
Später ansehen
Duo Cheng, …
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Später ansehen
Gati Aher, …
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Später ansehen
Dachuan Shi, …
Inflow, Outflow and Reciprocity In Machine Learning
Später ansehen
