Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ...
We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the reconstruction of frames during which the hand is stably holding the object. We first develop the stable grasp definition based on the intuition that the in-contact area between the hand and object should remain stable. By...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2312.15719 https://arxiv.org/abs/2312.15719 |
id |
ftdatacite:10.48550/arxiv.2312.15719 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2312.15719 2024-06-09T07:44:08+00:00 Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... Zhu, Zhifan Damen, Dima 2023 https://dx.doi.org/10.48550/arxiv.2312.15719 https://arxiv.org/abs/2312.15719 unknown arXiv Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences CreativeWork article Preprint Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2312.15719 2024-05-13T10:56:00Z We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the reconstruction of frames during which the hand is stably holding the object. We first develop the stable grasp definition based on the intuition that the in-contact area between the hand and object should remain stable. By analysing the 3D ARCTIC dataset, we identify stable grasp durations and showcase that objects in stable grasps move within a single degree of freedom (1-DoF). We thereby propose a method to jointly optimise all frames within a stable grasp, minimising object motions to a latent 1-DoF. Finally, we extend the knowledge to in-the-wild videos by labelling 2.4K clips of stable grasps. Our proposed EPIC-Grasps dataset includes 390 object instances of 9 categories, featuring stable grasps from videos of daily interactions in 141 environments. Without 3D ground truth, we use stable contact areas and 2D projection masks to assess the HO-SGR task in the wild. We evaluate relevant methods and our approach preserves ... : webpage: https://zhifanzhu.github.io/getagrip ... Article in Journal/Newspaper Arctic DataCite Metadata Store (German National Library of Science and Technology) Arctic |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Zhu, Zhifan Damen, Dima Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the reconstruction of frames during which the hand is stably holding the object. We first develop the stable grasp definition based on the intuition that the in-contact area between the hand and object should remain stable. By analysing the 3D ARCTIC dataset, we identify stable grasp durations and showcase that objects in stable grasps move within a single degree of freedom (1-DoF). We thereby propose a method to jointly optimise all frames within a stable grasp, minimising object motions to a latent 1-DoF. Finally, we extend the knowledge to in-the-wild videos by labelling 2.4K clips of stable grasps. Our proposed EPIC-Grasps dataset includes 390 object instances of 9 categories, featuring stable grasps from videos of daily interactions in 141 environments. Without 3D ground truth, we use stable contact areas and 2D projection masks to assess the HO-SGR task in the wild. We evaluate relevant methods and our approach preserves ... : webpage: https://zhifanzhu.github.io/getagrip ... |
format |
Article in Journal/Newspaper |
author |
Zhu, Zhifan Damen, Dima |
author_facet |
Zhu, Zhifan Damen, Dima |
author_sort |
Zhu, Zhifan |
title |
Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
title_short |
Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
title_full |
Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
title_fullStr |
Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
title_full_unstemmed |
Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos ... |
title_sort |
get a grip: reconstructing hand-object stable grasps in egocentric videos ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2312.15719 https://arxiv.org/abs/2312.15719 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_rights |
Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2312.15719 |
_version_ |
1801372933687345152 |