| Submission name | fastsam_test | ||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Nov. 29, 2024, 12:53 p.m. | ||||||||||||||||||||||||||
| User | zyMeteroid | ||||||||||||||||||||||||||
| Task | Model-free 2D detection of unseen objects | ||||||||||||||||||||||||||
| Dataset | HOPEv2 | ||||||||||||||||||||||||||
| Description | |||||||||||||||||||||||||||
| Evaluation scores |
|
| User | zyMeteroid |
|---|---|
| Publication | not yet |
| Implementation | Pytorch |
| Training image modalities | RGB |
| Test image modalities | RGB |
| Description | Submitted to: BOP Challenge 2024 Training data: Zero-shot Onboarding data: static onboarding Notes: 1. Reconstruction: We use Gaussiansplatting for reconstruction. All static onboarding images are used. 2. Pose Estimation: based on FastSAM and dinov2. Authors: Xingyu Liu, Yingyue Li, Chengxi Li, Gu Wang, Chenyangguang Zhang, Ziqin huang, Xiangyang Ji. Tsinghua University. |
| Computer specifications | RTX3090 |