| User | sp9103 |
|---|---|
| Publication | Genflow: Generalizable recurrent flow for 6d pose refinement of novel objects, CVPR 2024 |
| Implementation | - |
| Implementation | - |
| Views | single |
| Test image modalities | RGB |
| 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 | ||
|---|---|---|---|---|
| 2024-09-23 07:43 | - | HOPEv2 | ||
| 2024-09-23 11:31 | - | HANDAL | ||
| 2024-09-23 13:06 | threshold = 0.6 | HOPEv2 | ||
| 2024-09-24 01:30 | threshold = 0.6 | HANDAL | ||
| 2024-09-26 13:25 | threshold = 0.6 | HOT3D | ||
| 2024-09-27 03:00 | threshold = 0.6 | LM-O | ||
| 2024-09-27 03:01 | threshold = 0.6 | T-LESS | ||
| 2024-09-27 03:02 | threshold = 0.6 | TUD-L | ||
| 2024-09-27 03:02 | threshold = 0.6 | IC-BIN | ||
| 2024-09-27 03:03 | threshold = 0.6 | HB | ||
| 2024-09-27 03:04 | threshold = 0.6 | YCB-V | ||
| 2024-09-27 03:16 | threshold = 0.2 | ITODD | ||
| 2024-11-02 23:18 | - | LM-O | ||
| 2024-11-02 23:19 | - | T-LESS | ||
| 2024-11-02 23:19 | - | TUD-L | ||
| 2024-11-02 23:19 | - | IC-BIN | ||
| 2024-11-02 23:20 | - | ITODD | ||
| 2024-11-02 23:20 | - | HB | ||
| 2024-11-02 23:20 | - | YCB-V |