2020 · 85 citations · 71 references
ComputingComputer Science3D ModelingComputer VisionNonverbal Communication3D ReconstructionAction RecognitionBody ImageBody RepresentationFacial ExpressionMulti-view GeometryBody Part RepresentationFacial Expression RepresentationHuman Body ReconstructionView-dependent Appearance ModelingViews
This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cam- eras are used to capture 772 distinctive subjects across gen- der, ethnicity, age, and physical condition. With the mul- tiview image streams, we reconstruct high fidelity body ex- pressions using 3D mesh models, which allows representing view-specific appearance using their canonical atlas. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complemen- tary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets.
71
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Zhe Cao, Tomas Simon, Shih-En Wei et al. · 2017 · 7.3K citations
Structure-from-Motion Revisited
Johannes L. Schönberger, Jan‐Michael Frahm · 2016 · 5.8K citations
Matthew Loper, Naureen Mahmood, Javier Romero et al. · ACM Transactions on Graphics · 2015 · 3.6K citations
Architecture, Anatomy, 3D Modeling +15