FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313463976> ?p ?o ?g. }

• W4313463976 abstract "A large number of diverse data sets are necessary for networks to predict human body parameters and reconstruct 3D body models from images. Due to the high cost of motion capture and body scanning, high precision pose and body shape parameters are difficult to obtain. Meanwhile, existing datasets cannot meet the requirements in terms of diversity, size, and data accuracy for practical applications. Inspired by the construction schemes of various datasets, we design and construct a large multi-view 3D human body reconstruction dataset (3DMVHumanBP) with more types of supervised data. By recording the different poses of 25 women and 25 men in a green screen laboratory from six perspectives, we constructed a complete large multi-view 3D body posture dataset containing 340, 000 images. It is worth noting that, we innovatively propose a body dimension prior to the constrained human parametric model construction strategy to provide high-precision ground truth parameters of the human body SMPL models. In addition, we also designed a dense UV data generation method based on human body boundary and mask mapping to provide high-quality dense UV data, which more closely fits the features of the human images. It makes up for the defect that few existing data sets can only provide sparse UV data. In the experiment, the effectiveness and advantages of the data set constructed by us in network training are verified. Compared with the training of existing datasets, the mainstream network models trained on our datasets can significantly improve their prediction accuracy and robustness, thanks to the monitoring data of multiple kinds of high-precision human model parameters provided by 3DMVHumanBP. We hope that the human body dataset construction scheme we designed can provide ideas for building large-scale high precision human body datasets in the future." @default.
• W4313463976 created "2023-01-06" @default.
• W4313463976 creator A5011919230 @default.
• W4313463976 creator A5033354384 @default.
• W4313463976 creator A5036619239 @default.
• W4313463976 creator A5043007847 @default.
• W4313463976 creator A5045491581 @default.
• W4313463976 creator A5049055019 @default.
• W4313463976 date "2022-11-03" @default.
• W4313463976 modified "2023-09-30" @default.
• W4313463976 title "Multi-view 3D Human Physique Dataset Construction For Robust Digital Human Modeling of Natural Scenes" @default.
• W4313463976 cites W1861492603 @default.
• W4313463976 cites W2080873731 @default.
• W4313463976 cites W2099333815 @default.
• W4313463976 cites W2101032778 @default.
• W4313463976 cites W2135533529 @default.
• W4313463976 cites W2322085139 @default.
• W4313463976 cites W2330634884 @default.
• W4313463976 cites W2483862638 @default.
• W4313463976 cites W2573098616 @default.
• W4313463976 cites W2797184202 @default.
• W4313463976 cites W2895748257 @default.
• W4313463976 cites W2910824554 @default.
• W4313463976 cites W2949924544 @default.
• W4313463976 cites W2963527086 @default.
• W4313463976 cites W2963876278 @default.
• W4313463976 cites W2963995996 @default.
• W4313463976 cites W2964145484 @default.
• W4313463976 cites W2971856312 @default.
• W4313463976 cites W3025800305 @default.
• W4313463976 cites W3035551320 @default.
• W4313463976 cites W3119105168 @default.
• W4313463976 cites W3150298754 @default.
• W4313463976 cites W4205116876 @default.
• W4313463976 doi "https://doi.org/10.1145/3571662.3571675" @default.
• W4313463976 hasPublicationYear "2022" @default.
• W4313463976 type Work @default.
• W4313463976 citedByCount "0" @default.
• W4313463976 crossrefType "proceedings-article" @default.
• W4313463976 hasAuthorship W4313463976A5011919230 @default.
• W4313463976 hasAuthorship W4313463976A5033354384 @default.
• W4313463976 hasAuthorship W4313463976A5036619239 @default.
• W4313463976 hasAuthorship W4313463976A5043007847 @default.
• W4313463976 hasAuthorship W4313463976A5045491581 @default.
• W4313463976 hasAuthorship W4313463976A5049055019 @default.
• W4313463976 hasConcept C104114177 @default.
• W4313463976 hasConcept C104317684 @default.
• W4313463976 hasConcept C105795698 @default.
• W4313463976 hasConcept C117251300 @default.
• W4313463976 hasConcept C119857082 @default.
• W4313463976 hasConcept C124101348 @default.
• W4313463976 hasConcept C146849305 @default.
• W4313463976 hasConcept C153180895 @default.
• W4313463976 hasConcept C154945302 @default.
• W4313463976 hasConcept C177264268 @default.
• W4313463976 hasConcept C185592680 @default.
• W4313463976 hasConcept C193293595 @default.
• W4313463976 hasConcept C199360897 @default.
• W4313463976 hasConcept C202444582 @default.
• W4313463976 hasConcept C31972630 @default.
• W4313463976 hasConcept C33676613 @default.
• W4313463976 hasConcept C33923547 @default.
• W4313463976 hasConcept C41008148 @default.
• W4313463976 hasConcept C48007421 @default.
• W4313463976 hasConcept C55493867 @default.
• W4313463976 hasConcept C58489278 @default.
• W4313463976 hasConcept C63479239 @default.
• W4313463976 hasConceptScore W4313463976C104114177 @default.
• W4313463976 hasConceptScore W4313463976C104317684 @default.
• W4313463976 hasConceptScore W4313463976C105795698 @default.
• W4313463976 hasConceptScore W4313463976C117251300 @default.
• W4313463976 hasConceptScore W4313463976C119857082 @default.
• W4313463976 hasConceptScore W4313463976C124101348 @default.
• W4313463976 hasConceptScore W4313463976C146849305 @default.
• W4313463976 hasConceptScore W4313463976C153180895 @default.
• W4313463976 hasConceptScore W4313463976C154945302 @default.
• W4313463976 hasConceptScore W4313463976C177264268 @default.
• W4313463976 hasConceptScore W4313463976C185592680 @default.
• W4313463976 hasConceptScore W4313463976C193293595 @default.
• W4313463976 hasConceptScore W4313463976C199360897 @default.
• W4313463976 hasConceptScore W4313463976C202444582 @default.
• W4313463976 hasConceptScore W4313463976C31972630 @default.
• W4313463976 hasConceptScore W4313463976C33676613 @default.
• W4313463976 hasConceptScore W4313463976C33923547 @default.
• W4313463976 hasConceptScore W4313463976C41008148 @default.
• W4313463976 hasConceptScore W4313463976C48007421 @default.
• W4313463976 hasConceptScore W4313463976C55493867 @default.
• W4313463976 hasConceptScore W4313463976C58489278 @default.
• W4313463976 hasConceptScore W4313463976C63479239 @default.
• W4313463976 hasLocation W43134639761 @default.
• W4313463976 hasOpenAccess W4313463976 @default.
• W4313463976 hasPrimaryLocation W43134639761 @default.
• W4313463976 hasRelatedWork W1632903234 @default.
• W4313463976 hasRelatedWork W2035976912 @default.
• W4313463976 hasRelatedWork W2144792299 @default.
• W4313463976 hasRelatedWork W2158782090 @default.
• W4313463976 hasRelatedWork W2541791370 @default.
• W4313463976 hasRelatedWork W2624451073 @default.
• W4313463976 hasRelatedWork W2746445126 @default.
• W4313463976 hasRelatedWork W2914179169 @default.

• next