We lifted 6 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| nv-nguyen/cnos | canonical | 2 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| get_rel_pos | Ran | nv-nguyen/cnos/segment_anything/modeling/image_encoder.py code served (permissive licence) · get_code("733d7f0bedcb74c2") |
| window_partition | Ran | nv-nguyen/cnos/segment_anything/modeling/image_encoder.py code served (permissive licence) · get_code("105fa08885dc36cc") |
| build_sam_vit_b | Not yet run | nv-nguyen/cnos/segment_anything/build_sam.py code served (permissive licence) · get_code("f9bc5f31ce61cee8") |
| build_sam_vit_h | Not yet run | nv-nguyen/cnos/segment_anything/build_sam.py code served (permissive licence) · get_code("6b77c1f11fff3ed6") |
| build_sam_vit_l | Not yet run | nv-nguyen/cnos/segment_anything/build_sam.py code served (permissive licence) · get_code("3f8890e695469246") |
| window_unpartition | Not yet run | nv-nguyen/cnos/segment_anything/modeling/image_encoder.py code served (permissive licence) · get_code("27be441cc8213e52") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a simple three-stage approach to segment unseen objects in RGB images using their CAD models. Leveraging recent powerful foundation models, DINOv2 and Segment Anything, we create descriptors and generate proposals, including binary masks for a given input RGB image. By matching proposals with reference descriptors created from CAD models, we achieve precise object ID assignment along with modal masks. We experimentally demonstrate that our method achieves state-of-the-art results in CAD-based novel object segmentation, surpassing existing approaches on the seven core datasets of the BOP challenge by 19.8% AP using the same BOP evaluation protocol. Our source code is available at https://github.com/nv-nguyen/cnos.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.11067")
get_code_for_paper("2307.11067")
have("2307.11067")
Connect an agent — have() is free.