The presented results were achieved by the refinement-free version of FoundPose (row 1 of Table 1 in [A]).

In this submission, FoundPose uses default CNOS-FastSAM [B] segmentations provided for BOP'23. For pose estimation, the method uses features from layer 18 of DINOv2 (ViT-L) with registers [C].

Note that FoundPose doesn't do any task-specific training -- it only uses frozen FastSAM (via CNOS) and frozen DINOv2.

[A] Anonymous: FoundPose: Unseen Object Pose Estimation with Foundation Features.

[B] Nguyen et al.: CNOS: A Strong Baseline for CAD-based Novel Object Segmentation, ICCVW 2023.

[C] Darcet et al.: Vision transformers need registers, arXiv 2023.