{"ID":2889079,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21555","arxiv_id":"2507.21555","title":"Multi-View Reconstruction with Global Context for 3D Anomaly Detection","abstract":"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.","short_abstract":"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 hig...","url_abs":"https://arxiv.org/abs/2507.21555","url_pdf":"https://arxiv.org/pdf/2507.21555v1","authors":"[\"Yihan Sun\",\"Yuqi Cheng\",\"Yunkang Cao\",\"Yuxin Zhang\",\"Weiming Shen\"]","published":"2025-07-29T07:37:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}