SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings
Abstract
We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at surfemb.github.io.
Cite
Text
Haugaard and Buch. "SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00663Markdown
[Haugaard and Buch. "SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/haugaard2022cvpr-surfemb/) doi:10.1109/CVPR52688.2022.00663BibTeX
@inproceedings{haugaard2022cvpr-surfemb,
title = {{SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings}},
author = {Haugaard, Rasmus Laurvig and Buch, Anders Glent},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {6749-6758},
doi = {10.1109/CVPR52688.2022.00663},
url = {https://mlanthology.org/cvpr/2022/haugaard2022cvpr-surfemb/}
}