Multi-View Reconstruction with Global Context for 3D Anomaly Detection
This addresses the need for improved anomaly detection in industrial quality inspection, but it appears incremental as it builds on existing reconstruction-based methods by adding global context.
The paper tackles the problem of performance degradation in high-precision 3D anomaly detection for industrial quality inspection by proposing Multi-View Reconstruction (MVR), which converts point clouds into multi-view images to enhance global information learning, achieving 89.6% object-wise AU-ROC and 95.7% point-wise AU-ROC on the Real3D-AD benchmark.
3D anomaly detection is critical in industrial quality inspection. While existing methods achieve notable progress, their performance degrades in high-precision 3D anomaly detection due to insufficient global information. To address this, we propose Multi-View Reconstruction (MVR), a method that losslessly converts high-resolution point clouds into multi-view images and employs a reconstruction-based anomaly detection framework to enhance global information learning. Extensive experiments demonstrate the effectiveness of MVR, achieving 89.6\% object-wise AU-ROC and 95.7\% point-wise AU-ROC on the Real3D-AD benchmark.