| Submission name | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Sept. 23, 2024, 7:43 a.m. | ||||||||||||||
| User | sp9103 | ||||||||||||||
| Task | Model-based 6D detection of unseen objects | ||||||||||||||
| Dataset | HOPEv2 | ||||||||||||||
| Description | |||||||||||||||
| Evaluation scores |
|
| User | sp9103 |
|---|---|
| Publication | Genflow: Generalizable recurrent flow for 6d pose refinement of novel objects, CVPR 2024 |
| Implementation | - |
| Training image modalities | RGB-D |
| 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 1 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 |