Human pose estimation using deep learning: review, methodologies, progress and future research directions
Human pose estimation (HPE) has developed over the past decade into a vibrant field for
research with a variety of real-world applications like 3D reconstruction, virtual testing and re …
research with a variety of real-world applications like 3D reconstruction, virtual testing and re …
Phasemp: Robust 3d pose estimation via phase-conditioned human motion prior
We present a novel motion prior, called PhaseMP, modeling a probability distribution on
pose transitions conditioned by a frequency domain feature extracted from a periodic …
pose transitions conditioned by a frequency domain feature extracted from a periodic …
Mirror-aware neural humans
Human motion capture either requires multi-camera systems or is unreliable when using
single-view input due to depth ambiguities. Meanwhile, mirrors are readily available in …
single-view input due to depth ambiguities. Meanwhile, mirrors are readily available in …
M-NeRF: model-based human reconstruction from scratch with mirror-aware neural radiance fields
DA Ajisafe - 2023 - open.library.ubc.ca
Human motion capture either requires multi-camera systems or is unreliable using single-
view input due to depth ambiguities. Meanwhile, mirrors are readily available in urban …
view input due to depth ambiguities. Meanwhile, mirrors are readily available in urban …
From Synthetic to One-Shot Regression of Camera-Agnostic Human Performances
J Habekost, K Pang, T Shiratori, T Komura - International Conference on …, 2022 - Springer
Capturing accurate 3D human performances in global space from a static monocular video
is an ill-posed problem. It requires solving various depth ambiguities and information about …
is an ill-posed problem. It requires solving various depth ambiguities and information about …