Synthesis4AD generates controllable synthetic 3D defects via MPAS and MLLM to achieve state-of-the-art performance on Real3D-AD, MulSen-AD, and real industrial datasets.
Examining the source of defects from a mechanical perspective for 3d anomaly detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PCDiff applies instance-level multi-modal attention in a diffusion framework for anomaly generation and joint local-global reconstruction for detection, claiming superior fidelity and accuracy over prior methods.
citing papers explorer
-
Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection
Synthesis4AD generates controllable synthetic 3D defects via MPAS and MLLM to achieve state-of-the-art performance on Real3D-AD, MulSen-AD, and real industrial datasets.
-
Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection
PCDiff applies instance-level multi-modal attention in a diffusion framework for anomaly generation and joint local-global reconstruction for detection, claiming superior fidelity and accuracy over prior methods.