FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283702010> ?p ?o ?g. }

• W4283702010 endingPage "15" @default.
• W4283702010 startingPage "1" @default.
• W4283702010 abstract "3D symmetry detection is a fundamental problem in computer vision and graphics. Most prior works detect symmetry when the object model is fully known, few studies symmetry detection on objects with partial observation, such as single RGB-D images. Recent work addresses the problem of detecting symmetries from incomplete data with a deep neural network by leveraging the dense and accurate symmetry annotations. However, due to the tedious labeling process, full symmetry annotations are not always practically available. In this work, we present a 3D symmetry detection approach to detect symmetry from single-view RGB-D images without using symmetry supervision. The key idea is to train the network in a weakly-supervised learning manner to complete the shape based on the predicted symmetry such that the completed shape be similar to existing plausible shapes. To achieve this, we first propose a discriminative variational autoencoder to learn the shape prior in order to determine whether a 3D shape is plausible or not. Based on the learned shape prior, a symmetry detection network is present to predict symmetries that produce shapes with high shape plausibility when completed based on those symmetries. Moreover, to facilitate end-to-end network training and multiple symmetry detection, we introduce a new symmetry parametrization for the learning-based symmetry estimation of both reflectional and rotational symmetry. The proposed approach, coupled symmetry detection with shape completion, essentially learns the symmetry-aware shape prior, facilitating more accurate and robust symmetry detection. Experiments demonstrate that the proposed method is capable of detecting reflectional and rotational symmetries accurately, and shows good generality in challenging scenarios, such as objects with heavy occlusion and scanning noise. Moreover, it achieves state-of-the-art performance, improving the F1-score over the existing supervised learning method by 2&#x0025;-11&#x0025; on the ShapeNet and ScanNet datasets." @default.
• W4283702010 created "2022-06-30" @default.
• W4283702010 creator A5000248352 @default.
• W4283702010 creator A5045579536 @default.
• W4283702010 creator A5052231789 @default.
• W4283702010 creator A5053112608 @default.
• W4283702010 creator A5063760812 @default.
• W4283702010 creator A5071074935 @default.
• W4283702010 date "2022-01-01" @default.
• W4283702010 modified "2023-09-26" @default.
• W4283702010 title "Learning to Detect 3D Symmetry From Single-View RGB-D Images With Weak Supervision" @default.
• W4283702010 cites W1566328901 @default.
• W4283702010 cites W1580065766 @default.
• W4283702010 cites W168218614 @default.
• W4283702010 cites W1953319329 @default.
• W4283702010 cites W1977798567 @default.
• W4283702010 cites W1995050439 @default.
• W4283702010 cites W2014667763 @default.
• W4283702010 cites W2018259456 @default.
• W4283702010 cites W2052415172 @default.
• W4283702010 cites W2060206980 @default.
• W4283702010 cites W2072202468 @default.
• W4283702010 cites W2083163329 @default.
• W4283702010 cites W2086984226 @default.
• W4283702010 cites W2089841394 @default.
• W4283702010 cites W2097307110 @default.
• W4283702010 cites W2115579991 @default.
• W4283702010 cites W2129098897 @default.
• W4283702010 cites W2130518695 @default.
• W4283702010 cites W2146527621 @default.
• W4283702010 cites W2147824893 @default.
• W4283702010 cites W2151823074 @default.
• W4283702010 cites W2194775991 @default.
• W4283702010 cites W2552414813 @default.
• W4283702010 cites W2559882727 @default.
• W4283702010 cites W2560722161 @default.
• W4283702010 cites W2594519801 @default.
• W4283702010 cites W2607081783 @default.
• W4283702010 cites W2746791238 @default.
• W4283702010 cites W2756627269 @default.
• W4283702010 cites W2763391026 @default.
• W4283702010 cites W2796426482 @default.
• W4283702010 cites W2798748179 @default.
• W4283702010 cites W2885151039 @default.
• W4283702010 cites W2886499109 @default.
• W4283702010 cites W2898348749 @default.
• W4283702010 cites W2903435684 @default.
• W4283702010 cites W2904332125 @default.
• W4283702010 cites W2962849139 @default.
• W4283702010 cites W2962888833 @default.
• W4283702010 cites W2963177347 @default.
• W4283702010 cites W2963627347 @default.
• W4283702010 cites W2963892972 @default.
• W4283702010 cites W2963926543 @default.
• W4283702010 cites W2980847173 @default.
• W4283702010 cites W2989645276 @default.
• W4283702010 cites W2997088169 @default.
• W4283702010 cites W3002271958 @default.
• W4283702010 cites W3034597466 @default.
• W4283702010 cites W3035624836 @default.
• W4283702010 cites W3092774272 @default.
• W4283702010 cites W3103740959 @default.
• W4283702010 cites W3108839208 @default.
• W4283702010 cites W3129588459 @default.
• W4283702010 cites W3132706213 @default.
• W4283702010 cites W3168648756 @default.
• W4283702010 cites W3174726247 @default.
• W4283702010 cites W3181777995 @default.
• W4283702010 cites W3201663056 @default.
• W4283702010 cites W4230738288 @default.
• W4283702010 cites W4232014598 @default.
• W4283702010 cites W4232787297 @default.
• W4283702010 cites W4241829961 @default.
• W4283702010 cites W4247329067 @default.
• W4283702010 doi "https://doi.org/10.1109/tpami.2022.3186876" @default.
• W4283702010 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35763472" @default.
• W4283702010 hasPublicationYear "2022" @default.
• W4283702010 type Work @default.
• W4283702010 citedByCount "19" @default.
• W4283702010 countsByYear W42837020102022 @default.
• W4283702010 countsByYear W42837020102023 @default.
• W4283702010 crossrefType "journal-article" @default.
• W4283702010 hasAuthorship W4283702010A5000248352 @default.
• W4283702010 hasAuthorship W4283702010A5045579536 @default.
• W4283702010 hasAuthorship W4283702010A5052231789 @default.
• W4283702010 hasAuthorship W4283702010A5053112608 @default.
• W4283702010 hasAuthorship W4283702010A5063760812 @default.
• W4283702010 hasAuthorship W4283702010A5071074935 @default.
• W4283702010 hasBestOaLocation W42837020101 @default.
• W4283702010 hasConcept C101738243 @default.
• W4283702010 hasConcept C108583219 @default.
• W4283702010 hasConcept C121332964 @default.
• W4283702010 hasConcept C125881977 @default.
• W4283702010 hasConcept C133978748 @default.
• W4283702010 hasConcept C153180895 @default.
• W4283702010 hasConcept C154945302 @default.
• W4283702010 hasConcept C192423722 @default.
• W4283702010 hasConcept C204795200 @default.

• next