FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312260328> ?p ?o ?g. }

• W4312260328 endingPage "428" @default.
• W4312260328 startingPage "412" @default.
• W4312260328 abstract "Estimating 3D human pose and shape from 2D images is a crucial yet challenging task. While prior methods with model-based representations can perform reasonably well on whole-body images, they often fail when parts of the body are occluded or outside the frame. Moreover, these results usually do not faithfully capture the human silhouettes due to their limited representation power of deformable models (e.g., representing only the naked body). An alternative approach is to estimate dense vertices of a predefined template body in the image space. Such representations are effective in localizing vertices within an image but cannot handle out-of-frame body parts. In this work, we learn dense human body estimation that is robust to partial observations. We explicitly model the visibility of human joints and vertices in the x, y, and z axes separately. The visibility in x and y axes help distinguishing out-of-frame cases, and the visibility in depth axis corresponds to occlusions (either self-occlusions or occlusions by other objects). We obtain pseudo ground-truths of visibility labels from dense UV correspondences and train a neural network to predict visibility along with 3D coordinates. We show that visibility can serve as 1) an additional signal to resolve depth ordering ambiguities of self-occluded vertices and 2) a regularization term when fitting a human body model to the predictions. Extensive experiments on multiple 3D human datasets demonstrate that visibility modeling significantly improves the accuracy of human body estimation, especially for partial-body cases. Our project page with code is at: https://github.com/chhankyao/visdb ." @default.
• W4312260328 created "2023-01-04" @default.
• W4312260328 creator A5009299466 @default.
• W4312260328 creator A5026010210 @default.
• W4312260328 creator A5053207994 @default.
• W4312260328 creator A5056443318 @default.
• W4312260328 creator A5063179713 @default.
• W4312260328 creator A5068985412 @default.
• W4312260328 date "2022-01-01" @default.
• W4312260328 modified "2023-09-26" @default.
• W4312260328 title "Learning Visibility for Robust Dense Human Body Estimation" @default.
• W4312260328 cites W1861492603 @default.
• W4312260328 cites W1967554269 @default.
• W4312260328 cites W2101032778 @default.
• W4312260328 cites W2108598243 @default.
• W4312260328 cites W2194775991 @default.
• W4312260328 cites W2483862638 @default.
• W4312260328 cites W2573098616 @default.
• W4312260328 cites W2573854917 @default.
• W4312260328 cites W2797515701 @default.
• W4312260328 cites W2798637590 @default.
• W4312260328 cites W2888934629 @default.
• W4312260328 cites W2895748257 @default.
• W4312260328 cites W2962754033 @default.
• W4312260328 cites W2963150697 @default.
• W4312260328 cites W2963508807 @default.
• W4312260328 cites W2963598138 @default.
• W4312260328 cites W2963876278 @default.
• W4312260328 cites W2963907666 @default.
• W4312260328 cites W2963995996 @default.
• W4312260328 cites W2965523038 @default.
• W4312260328 cites W2971467054 @default.
• W4312260328 cites W2978956737 @default.
• W4312260328 cites W2981514602 @default.
• W4312260328 cites W2981637078 @default.
• W4312260328 cites W2981978060 @default.
• W4312260328 cites W2982275673 @default.
• W4312260328 cites W2998273692 @default.
• W4312260328 cites W3004162361 @default.
• W4312260328 cites W3035186639 @default.
• W4312260328 cites W3035291735 @default.
• W4312260328 cites W3035501466 @default.
• W4312260328 cites W3035551320 @default.
• W4312260328 cites W3107167007 @default.
• W4312260328 cites W3109877674 @default.
• W4312260328 cites W3110631859 @default.
• W4312260328 cites W3172644340 @default.
• W4312260328 cites W3174980830 @default.
• W4312260328 cites W3175199633 @default.
• W4312260328 cites W3204582936 @default.
• W4312260328 cites W4214517305 @default.
• W4312260328 cites W4214619583 @default.
• W4312260328 cites W4214684804 @default.
• W4312260328 cites W4214770715 @default.
• W4312260328 doi "https://doi.org/10.1007/978-3-031-19769-7_24" @default.
• W4312260328 hasPublicationYear "2022" @default.
• W4312260328 type Work @default.
• W4312260328 citedByCount "1" @default.
• W4312260328 countsByYear W43122603282023 @default.
• W4312260328 crossrefType "book-chapter" @default.
• W4312260328 hasAuthorship W4312260328A5009299466 @default.
• W4312260328 hasAuthorship W4312260328A5026010210 @default.
• W4312260328 hasAuthorship W4312260328A5053207994 @default.
• W4312260328 hasAuthorship W4312260328A5056443318 @default.
• W4312260328 hasAuthorship W4312260328A5063179713 @default.
• W4312260328 hasAuthorship W4312260328A5068985412 @default.
• W4312260328 hasBestOaLocation W43122603282 @default.
• W4312260328 hasConcept C120665830 @default.
• W4312260328 hasConcept C121332964 @default.
• W4312260328 hasConcept C123403432 @default.
• W4312260328 hasConcept C126042441 @default.
• W4312260328 hasConcept C153180895 @default.
• W4312260328 hasConcept C154945302 @default.
• W4312260328 hasConcept C177264268 @default.
• W4312260328 hasConcept C17744445 @default.
• W4312260328 hasConcept C193293595 @default.
• W4312260328 hasConcept C199360897 @default.
• W4312260328 hasConcept C199539241 @default.
• W4312260328 hasConcept C2776359362 @default.
• W4312260328 hasConcept C2776760102 @default.
• W4312260328 hasConcept C2781089380 @default.
• W4312260328 hasConcept C31972630 @default.
• W4312260328 hasConcept C41008148 @default.
• W4312260328 hasConcept C76155785 @default.
• W4312260328 hasConcept C94625758 @default.
• W4312260328 hasConceptScore W4312260328C120665830 @default.
• W4312260328 hasConceptScore W4312260328C121332964 @default.
• W4312260328 hasConceptScore W4312260328C123403432 @default.
• W4312260328 hasConceptScore W4312260328C126042441 @default.
• W4312260328 hasConceptScore W4312260328C153180895 @default.
• W4312260328 hasConceptScore W4312260328C154945302 @default.
• W4312260328 hasConceptScore W4312260328C177264268 @default.
• W4312260328 hasConceptScore W4312260328C17744445 @default.
• W4312260328 hasConceptScore W4312260328C193293595 @default.
• W4312260328 hasConceptScore W4312260328C199360897 @default.
• W4312260328 hasConceptScore W4312260328C199539241 @default.
• W4312260328 hasConceptScore W4312260328C2776359362 @default.
• W4312260328 hasConceptScore W4312260328C2776760102 @default.

• next