ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description. Shan, M., Feng, Q., Jau, Y., & Atanasov, N.
![ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex Autonomous systems need to understand the semantics and geometry of their surroundings in order to comprehend and safely execute object-level task specifications. This paper proposes an expressive yet compact model for joint object pose and shape optimization, and an associated optimization algorithm to infer an object-level map from multi-view RGB-D camera observations. The model is expressive because it captures the identities, positions, orientations, and shapes of objects in the environment. It is compact because it relies on a low-dimensional latent representation of implicit object shape, allowing onboard storage of large multi-category object maps. Different from other works that rely on a single object representation format, our approach has a bi-level object model that captures both the coarse level scale as well as the fine level shape details. Our approach is evaluated on the large-scale real-world ScanNet dataset and compared against state-of-the-art methods.
@article{
title = {ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description},
type = {article},
id = {c995ba53-f9cb-315e-99ed-d14918d99597},
created = {2024-02-27T12:42:43.222Z},
accessed = {2024-02-27},
file_attached = {true},
profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2024-11-29T09:07:30.813Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
citation_key = {Shan},
folder_uuids = {df28411a-ed7f-4991-8358-d39685eb4bf0,5a010301-acb6-4642-a6b2-8afaee1b741c},
private_publication = {false},
abstract = {Autonomous systems need to understand the semantics and geometry of their surroundings in order to comprehend and safely execute object-level task specifications. This paper proposes an expressive yet compact model for joint object pose and shape optimization, and an associated optimization algorithm to infer an object-level map from multi-view RGB-D camera observations. The model is expressive because it captures the identities, positions, orientations, and shapes of objects in the environment. It is compact because it relies on a low-dimensional latent representation of implicit object shape, allowing onboard storage of large multi-category object maps. Different from other works that rely on a single object representation format, our approach has a bi-level object model that captures both the coarse level scale as well as the fine level shape details. Our approach is evaluated on the large-scale real-world ScanNet dataset and compared against state-of-the-art methods.},
bibtype = {article},
author = {Shan, Mo and Feng, Qiaojun and Jau, You-Yi and Atanasov, Nikolay}
}Downloads: 0
{"_id":"S2txrFwRKaZ4YeCzv","bibbaseid":"shan-feng-jau-atanasov-ellipsdfjointobjectposeandshapeoptimizationwithabilevelellipsoidandsigneddistancefunctiondescription","author_short":["Shan, M.","Feng, Q.","Jau, Y.","Atanasov, N."],"bibdata":{"title":"ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description","type":"article","id":"c995ba53-f9cb-315e-99ed-d14918d99597","created":"2024-02-27T12:42:43.222Z","accessed":"2024-02-27","file_attached":"true","profile_id":"f1f70cad-e32d-3de2-a3c0-be1736cb88be","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2024-11-29T09:07:30.813Z","read":"true","starred":false,"authored":false,"confirmed":false,"hidden":false,"citation_key":"Shan","folder_uuids":"df28411a-ed7f-4991-8358-d39685eb4bf0,5a010301-acb6-4642-a6b2-8afaee1b741c","private_publication":false,"abstract":"Autonomous systems need to understand the semantics and geometry of their surroundings in order to comprehend and safely execute object-level task specifications. This paper proposes an expressive yet compact model for joint object pose and shape optimization, and an associated optimization algorithm to infer an object-level map from multi-view RGB-D camera observations. The model is expressive because it captures the identities, positions, orientations, and shapes of objects in the environment. It is compact because it relies on a low-dimensional latent representation of implicit object shape, allowing onboard storage of large multi-category object maps. Different from other works that rely on a single object representation format, our approach has a bi-level object model that captures both the coarse level scale as well as the fine level shape details. Our approach is evaluated on the large-scale real-world ScanNet dataset and compared against state-of-the-art methods.","bibtype":"article","author":"Shan, Mo and Feng, Qiaojun and Jau, You-Yi and Atanasov, Nikolay","bibtex":"@article{\n title = {ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description},\n type = {article},\n id = {c995ba53-f9cb-315e-99ed-d14918d99597},\n created = {2024-02-27T12:42:43.222Z},\n accessed = {2024-02-27},\n file_attached = {true},\n profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2024-11-29T09:07:30.813Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n citation_key = {Shan},\n folder_uuids = {df28411a-ed7f-4991-8358-d39685eb4bf0,5a010301-acb6-4642-a6b2-8afaee1b741c},\n private_publication = {false},\n abstract = {Autonomous systems need to understand the semantics and geometry of their surroundings in order to comprehend and safely execute object-level task specifications. This paper proposes an expressive yet compact model for joint object pose and shape optimization, and an associated optimization algorithm to infer an object-level map from multi-view RGB-D camera observations. The model is expressive because it captures the identities, positions, orientations, and shapes of objects in the environment. It is compact because it relies on a low-dimensional latent representation of implicit object shape, allowing onboard storage of large multi-category object maps. Different from other works that rely on a single object representation format, our approach has a bi-level object model that captures both the coarse level scale as well as the fine level shape details. Our approach is evaluated on the large-scale real-world ScanNet dataset and compared against state-of-the-art methods.},\n bibtype = {article},\n author = {Shan, Mo and Feng, Qiaojun and Jau, You-Yi and Atanasov, Nikolay}\n}","author_short":["Shan, M.","Feng, Q.","Jau, Y.","Atanasov, N."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/06ccebfc-e303-adb1-2b5a-740e5a1ba3ba/full_text.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"shan-feng-jau-atanasov-ellipsdfjointobjectposeandshapeoptimizationwithabilevelellipsoidandsigneddistancefunctiondescription","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["ellipsdf","joint","object","pose","shape","optimization","level","ellipsoid","signed","distance","function","description","shan","feng","jau","atanasov"],"title":"ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description","year":null}