FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226424937> ?p ?o ?g. }

• W4226424937 endingPage "1948" @default.
• W4226424937 startingPage "1938" @default.
• W4226424937 abstract "A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data becomes a major bottleneck, especially for scenes with occlusions in the wild. In this paper, we focus on the estimation of human pose and shape in the case of inter-person occlusions, while also handling object-human occlusions and self-occlusion. We propose a novel framework that synthesizes occlusion-aware silhouette and 2D keypoints data and directly regress to the SMPL pose and shape parameters. A neural 3D mesh renderer is exploited to enable silhouette supervision on the fly, which contributes to great improvements in shape estimation. In addition, keypoints-and-silhouette-driven training data in panoramic viewpoints are synthesized to compensate for the lack of viewpoint diversity in any existing dataset. Experimental results show that we are among the state-of-the-art on the 3DPW and 3DPW-Crowd datasets in terms of pose estimation accuracy. The proposed method evidently outperforms Mesh Transformer, 3DCrowdNet and ROMP in terms of shape estimation. Top performance is also achieved on SSP-3D in terms of shape prediction accuracy. Demo and code will be available at https://igame-lab.github.io/LASOR/." @default.
• W4226424937 created "2022-05-05" @default.
• W4226424937 creator A5004882269 @default.
• W4226424937 creator A5016255619 @default.
• W4226424937 creator A5045766331 @default.
• W4226424937 creator A5048048944 @default.
• W4226424937 creator A5084180515 @default.
• W4226424937 date "2022-01-01" @default.
• W4226424937 modified "2023-09-25" @default.
• W4226424937 title "LASOR: Learning Accurate 3D Human Pose and Shape via Synthetic Occlusion-Aware Data and Neural Mesh Rendering" @default.
• W4226424937 cites W1967554269 @default.
• W4226424937 cites W2071300943 @default.
• W4226424937 cites W2194775991 @default.
• W4226424937 cites W2573098616 @default.
• W4226424937 cites W2797184202 @default.
• W4226424937 cites W2798411580 @default.
• W4226424937 cites W2798637590 @default.
• W4226424937 cites W2895748257 @default.
• W4226424937 cites W2949924544 @default.
• W4226424937 cites W2962754033 @default.
• W4226424937 cites W2962954622 @default.
• W4226424937 cites W2963150697 @default.
• W4226424937 cites W2963515833 @default.
• W4226424937 cites W2963527086 @default.
• W4226424937 cites W2963677766 @default.
• W4226424937 cites W2963873475 @default.
• W4226424937 cites W2963876278 @default.
• W4226424937 cites W2963907666 @default.
• W4226424937 cites W2963995996 @default.
• W4226424937 cites W2971856312 @default.
• W4226424937 cites W2978956737 @default.
• W4226424937 cites W2981637078 @default.
• W4226424937 cites W2984349976 @default.
• W4226424937 cites W3004162361 @default.
• W4226424937 cites W3034750257 @default.
• W4226424937 cites W3035186639 @default.
• W4226424937 cites W3035191304 @default.
• W4226424937 cites W3107167007 @default.
• W4226424937 cites W3108651438 @default.
• W4226424937 cites W3109877674 @default.
• W4226424937 cites W3161298928 @default.
• W4226424937 cites W3175199633 @default.
• W4226424937 cites W4236667477 @default.
• W4226424937 cites W4251108253 @default.
• W4226424937 doi "https://doi.org/10.1109/tip.2022.3149229" @default.
• W4226424937 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35143398" @default.
• W4226424937 hasPublicationYear "2022" @default.
• W4226424937 type Work @default.
• W4226424937 citedByCount "3" @default.
• W4226424937 countsByYear W42264249372023 @default.
• W4226424937 crossrefType "journal-article" @default.
• W4226424937 hasAuthorship W4226424937A5004882269 @default.
• W4226424937 hasAuthorship W4226424937A5016255619 @default.
• W4226424937 hasAuthorship W4226424937A5045766331 @default.
• W4226424937 hasAuthorship W4226424937A5048048944 @default.
• W4226424937 hasAuthorship W4226424937A5084180515 @default.
• W4226424937 hasBestOaLocation W42264249372 @default.
• W4226424937 hasConcept C121684516 @default.
• W4226424937 hasConcept C153180895 @default.
• W4226424937 hasConcept C154945302 @default.
• W4226424937 hasConcept C164705383 @default.
• W4226424937 hasConcept C205711294 @default.
• W4226424937 hasConcept C2776268601 @default.
• W4226424937 hasConcept C31487907 @default.
• W4226424937 hasConcept C31972630 @default.
• W4226424937 hasConcept C41008148 @default.
• W4226424937 hasConcept C52102323 @default.
• W4226424937 hasConcept C58103923 @default.
• W4226424937 hasConcept C71924100 @default.
• W4226424937 hasConceptScore W4226424937C121684516 @default.
• W4226424937 hasConceptScore W4226424937C153180895 @default.
• W4226424937 hasConceptScore W4226424937C154945302 @default.
• W4226424937 hasConceptScore W4226424937C164705383 @default.
• W4226424937 hasConceptScore W4226424937C205711294 @default.
• W4226424937 hasConceptScore W4226424937C2776268601 @default.
• W4226424937 hasConceptScore W4226424937C31487907 @default.
• W4226424937 hasConceptScore W4226424937C31972630 @default.
• W4226424937 hasConceptScore W4226424937C41008148 @default.
• W4226424937 hasConceptScore W4226424937C52102323 @default.
• W4226424937 hasConceptScore W4226424937C58103923 @default.
• W4226424937 hasConceptScore W4226424937C71924100 @default.
• W4226424937 hasFunder F4320321001 @default.
• W4226424937 hasFunder F4320335777 @default.
• W4226424937 hasFunder F4320338469 @default.
• W4226424937 hasLocation W42264249371 @default.
• W4226424937 hasLocation W42264249372 @default.
• W4226424937 hasLocation W42264249373 @default.
• W4226424937 hasLocation W42264249374 @default.
• W4226424937 hasOpenAccess W4226424937 @default.
• W4226424937 hasPrimaryLocation W42264249371 @default.
• W4226424937 hasRelatedWork W1506834312 @default.
• W4226424937 hasRelatedWork W1597979091 @default.
• W4226424937 hasRelatedWork W1602425644 @default.
• W4226424937 hasRelatedWork W1766899219 @default.
• W4226424937 hasRelatedWork W2011792403 @default.
• W4226424937 hasRelatedWork W2103855095 @default.
• W4226424937 hasRelatedWork W2121864739 @default.
• W4226424937 hasRelatedWork W2891001608 @default.

• next