Submission name | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
Submission time (UTC) | Dec. 22, 2021, 6:09 p.m. | ||||||||||
User | surfemb | ||||||||||
Task | Model-based 6D localization of seen objects | ||||||||||
Dataset | ITODD | ||||||||||
Training model type | Default | ||||||||||
Training image type | Synthetic (only PBR images provided for BOP Challenge 2020 were used) | ||||||||||
Description | |||||||||||
Evaluation scores |
|
User | surfemb |
---|---|
Publication | Rasmus Laurvig Haugaard, Anders Glent Buch: SurfEmb, CVPR 2022 |
Implementation | https://github.com/rasmushaugaard/surfemb |
Training image modalities | RGB |
Test image modalities | RGB-D |
Description | SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings Compared to the paper:
We use the available detections from CosyPose, but were not able to find detection-only timings. We add our timing on top of the full CosyPose single-view RGB pipeline, resulting in conservative timings. |
Computer specifications | 1 x RTX 2080 |