Method: free6d(refine)

User jzhao12
Publication
Implementation https://github.com/JZhao12/free6d
Views Single
Test image modalities RGB
Description

Submitted to: BOP Challenge 2025, model-based 2D detection and 2D segmentation of unseen objects, BOP-Classic-Core (LM-O, T-LESS, TUD-L, IC-BIN, ITODD, HB, YCB-V), BOP'19 test targets.

Training data: none. Free6D is zero-shot: SAM 2.1 Hiera-L and DINOv3 ViT-L/16 are used with their public pretrained weights (sam2.1_hiera_large.pt, dinov3_vitl16_pretrain_lvd1689m), no fine-tuning on BOP data.

Onboarding data: 42 templates per object rendered with pyrender from the CAD model (viewpoints of the level-0 icosphere, camera distance 0.4 of the predefined poses, black background, uniform grey material for T-LESS). No real onboarding images.

Used 3D models: the default BOP CAD models (models/, models_cad/ for T-LESS).

Computer specifications Intel Core Ultra 9 285K, 24 cores; NVIDIA GeForce RTX 5070, 12 GB; Ubuntu 24.04.5 LTS, Linux 7.0.0-42-generic

Public submissions

Date Submission name Dataset
2026-11-12 10:24 free6d-refine-lmo LM-O
2026-11-12 10:24 free6d-refine-tless T-LESS
2026-11-12 10:25 free6d-refine-tudl TUD-L
2026-11-12 10:26 free6d-refine-icbin IC-BIN
2026-11-12 10:27 free6d-refine-itodd ITODD
2026-11-12 10:27 free6d-refine-hb HB
2026-11-12 10:28 free6d-refine-ycbv YCB-V