| Submission name | GMatch-SPP | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | May 3, 2025, 11:22 a.m. | ||||||||||
| User | yang2019901 | ||||||||||
| Task | Model-based 6D localization of seen objects | ||||||||||
| Dataset | HOPE | ||||||||||
| Description | NOTE: masks are manually classified with their object id. it's ONLY for performance test. Pipeline: SuperPoint -> GMatch -> RANSAC -> ICP. bbox is used instead of segmentation. | ||||||||||
| Evaluation scores |
|
| User | yang2019901 |
|---|---|
| Publication | |
| Implementation | |
| Training image modalities | None |
| Test image modalities | RGB-D |
| Description | Researchs on the pose estimation pipeline based on feature matching, which is compose of a keypoint descriptor, a feature matcher, a geometric solver and a pose refiner. GMatch is the name of our proposed matcher.
[1] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60:91–110, 2004. [2] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: An efficient alternative to sift or surf. In 2011 International conference on computer vision, pages 2564–2571. Ieee, 2011. [3] Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich. Superpoint: Self-supervised interest point detection and description. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 224–236, 2018. [4] Philipp Lindenberger, Paul-Edouard Sarlin, and Marc Pollefeys. Lightglue: Local feature matching at light speed. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 17627–17638, 2023. |
| Computer specifications | i5-12400F (+ RTX4060, for lightglue and superpoint only) + 8G RAM, Ubuntu20.04 (WSL) |