| User | sp9103 |
|---|---|
| Publication | Genflow: Generalizable recurrent flow for 6d pose refinement of novel objects, CVPR 2024 |
| Implementation | - |
| Implementation | - |
| Views | single |
| Test image modalities | RGB-D |
| Description | Submitted to: BOP Challenge 2024 Training data: MegaPose-GSO and MegaPose-ShapeNetCore Used 3D models: Default, Notes: We use GigaPose [A] to extract 5 hypothesis and run GenFlow[B]. In this submission, CNOS_fastSAM [A] detections are used [A] Nguyen et al.: GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence, CVPR 2024. [B] Genflow: Generalizable recurrent flow for 6d pose refinement of novel objects, CVPR 2024 |
| Computer specifications | RTX 3090 Ti |
| Date | Submission name | Dataset | ||
|---|---|---|---|---|
| 2024-09-13 23:05 | threshold = 0.0 | LM-O | ||
| 2024-09-13 23:05 | threshold = 0.0 | T-LESS | ||
| 2024-09-13 23:06 | threshold = 0.0 | TUD-L | ||
| 2024-09-13 23:06 | threshold = 0.0 | IC-BIN | ||
| 2024-09-13 23:07 | threshold = 0.0 | ITODD | ||
| 2024-09-13 23:07 | threshold = 0.0 | HB | ||
| 2024-09-13 23:07 | threshold = 0.0 | YCB-V |