4,147 high-resolution 3D point cloud scans and RGB images across 10 categories. First comprehensive 3D anomaly detection benchmark.
6 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.
| # | Model | Org | Submitted | Paper / code | auroc |
|---|---|---|---|---|---|
| 01 | CMDR-IADOSS | Research | Mar 2025 | Cross-Modal Mapping and Dual-Branch Reconstruction for 2… | 97.30 |
| 02 | MTSJMOSS | Research | Mar 2025 | Cross-Modal Mapping and Dual-Branch Reconstruction for 2… | 95.70 |
| 03 | CFMOSS | Research | Mar 2025 | Cross-Modal Mapping and Dual-Branch Reconstruction for 2… | 95.40 |
| 04 | 3D-ADNASOSS | Anonymous (ECCV 2024) | Mar 2025 | Cross-Modal Mapping and Dual-Branch Reconstruction for 2… | 95.10 |
| 05 | M3DMOSS | Fudan University / Alibaba | Mar 2023 | Multimodal Industrial Anomaly Detection via Hybrid Fusio… | 94.50 |
| 06 | BTF (Back to the Feature)OSS | Weizmann Institute | Mar 2022 | Back to the Feature: Classical 3D Features are (Almost) … | 86.50 |
Each row below marks a model that broke the previous record on auroc. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.
Higher scores win. Each subsequent entry improved upon the previous best.
Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.