Matches in SemOpenAlex for { <https://semopenalex.org/work/W2769015737> ?p ?o ?g. }
- W2769015737 abstract "Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs). The first weakness of this approach is the presence of perspective distortion in the 2D depth map. While the depth map is intrinsically 3D data, many previous methods treat depth maps as 2D images that can distort the shape of the actual object through projection from 3D to 2D space. This compels the network to perform perspective distortion-invariant estimation. The second weakness of the conventional approach is that directly regressing 3D coordinates from a 2D image is a highly non-linear mapping, which causes difficulty in the learning procedure. To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel likelihood for each keypoint. We design our model as a 3D CNN that provides accurate estimates while running in real-time. Our system outperforms previous methods in almost all publicly available 3D hand and human pose estimation datasets and placed first in the HANDS 2017 frame-based 3D hand pose estimation challenge. The code is available in this https URL." @default.
- W2769015737 created "2017-12-04" @default.
- W2769015737 creator A5005534094 @default.
- W2769015737 creator A5046504049 @default.
- W2769015737 creator A5073032930 @default.
- W2769015737 date "2017-11-20" @default.
- W2769015737 modified "2023-09-27" @default.
- W2769015737 title "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map." @default.
- W2769015737 cites W1500711968 @default.
- W2769015737 cites W1515963346 @default.
- W2769015737 cites W1633557510 @default.
- W2769015737 cites W1912860515 @default.
- W2769015737 cites W1920022804 @default.
- W2769015737 cites W1928739709 @default.
- W2769015737 cites W1974700302 @default.
- W2769015737 cites W1977039804 @default.
- W2769015737 cites W1990947293 @default.
- W2769015737 cites W2000205118 @default.
- W2769015737 cites W2060280062 @default.
- W2769015737 cites W2075156252 @default.
- W2769015737 cites W2093414253 @default.
- W2769015737 cites W2110619642 @default.
- W2769015737 cites W2131213558 @default.
- W2769015737 cites W2136340340 @default.
- W2769015737 cites W2169172998 @default.
- W2769015737 cites W2194775991 @default.
- W2769015737 cites W2210697964 @default.
- W2769015737 cites W2211722331 @default.
- W2769015737 cites W2218414108 @default.
- W2769015737 cites W2229637417 @default.
- W2769015737 cites W2303693074 @default.
- W2769015737 cites W2341862707 @default.
- W2769015737 cites W2466332079 @default.
- W2769015737 cites W2473634362 @default.
- W2769015737 cites W2518780600 @default.
- W2769015737 cites W2521041279 @default.
- W2769015737 cites W2605462541 @default.
- W2769015737 cites W2605951450 @default.
- W2769015737 cites W2619078928 @default.
- W2769015737 cites W2724168988 @default.
- W2769015737 cites W2727891399 @default.
- W2769015737 cites W2737305288 @default.
- W2769015737 cites W2738421384 @default.
- W2769015737 cites W2738493602 @default.
- W2769015737 cites W2750326862 @default.
- W2769015737 cites W2753240668 @default.
- W2769015737 cites W2777106508 @default.
- W2769015737 cites W2796453247 @default.
- W2769015737 cites W2949117887 @default.
- W2769015737 cites W2949677570 @default.
- W2769015737 cites W2950762923 @default.
- W2769015737 cites W2952422028 @default.
- W2769015737 cites W2953357832 @default.
- W2769015737 cites W2963474899 @default.
- W2769015737 cites W64404897 @default.
- W2769015737 cites W753012316 @default.
- W2769015737 hasPublicationYear "2017" @default.
- W2769015737 type Work @default.
- W2769015737 sameAs 2769015737 @default.
- W2769015737 citedByCount "9" @default.
- W2769015737 countsByYear W27690157372018 @default.
- W2769015737 countsByYear W27690157372019 @default.
- W2769015737 countsByYear W27690157372020 @default.
- W2769015737 countsByYear W27690157372021 @default.
- W2769015737 crossrefType "posted-content" @default.
- W2769015737 hasAuthorship W2769015737A5005534094 @default.
- W2769015737 hasAuthorship W2769015737A5046504049 @default.
- W2769015737 hasAuthorship W2769015737A5073032930 @default.
- W2769015737 hasConcept C108583219 @default.
- W2769015737 hasConcept C11413529 @default.
- W2769015737 hasConcept C115961682 @default.
- W2769015737 hasConcept C126780896 @default.
- W2769015737 hasConcept C141268832 @default.
- W2769015737 hasConcept C153180895 @default.
- W2769015737 hasConcept C154945302 @default.
- W2769015737 hasConcept C187691185 @default.
- W2769015737 hasConcept C194257627 @default.
- W2769015737 hasConcept C2524010 @default.
- W2769015737 hasConcept C2776257435 @default.
- W2769015737 hasConcept C31258907 @default.
- W2769015737 hasConcept C31972630 @default.
- W2769015737 hasConcept C33923547 @default.
- W2769015737 hasConcept C36613465 @default.
- W2769015737 hasConcept C41008148 @default.
- W2769015737 hasConcept C52102323 @default.
- W2769015737 hasConcept C54170458 @default.
- W2769015737 hasConcept C57493831 @default.
- W2769015737 hasConcept C81363708 @default.
- W2769015737 hasConceptScore W2769015737C108583219 @default.
- W2769015737 hasConceptScore W2769015737C11413529 @default.
- W2769015737 hasConceptScore W2769015737C115961682 @default.
- W2769015737 hasConceptScore W2769015737C126780896 @default.
- W2769015737 hasConceptScore W2769015737C141268832 @default.
- W2769015737 hasConceptScore W2769015737C153180895 @default.
- W2769015737 hasConceptScore W2769015737C154945302 @default.
- W2769015737 hasConceptScore W2769015737C187691185 @default.
- W2769015737 hasConceptScore W2769015737C194257627 @default.
- W2769015737 hasConceptScore W2769015737C2524010 @default.
- W2769015737 hasConceptScore W2769015737C2776257435 @default.
- W2769015737 hasConceptScore W2769015737C31258907 @default.