SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.11067 · 2023

CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

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.

RepositoryRoleRan
nv-nguyen/cnos canonical 2 of 6
FunctionStatusWhere 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")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

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.