For Minimally-Clothed regions, we define the DSR-MC loss, which encourages a tight match between a rendered SMPL body and the minimally-clothed regions of the image.
Ranked #7 on 3D Human Pose Estimation on 3DPW (using extra training data)
We then train a novel network that concatenates the camera calibration to the image features and uses these together to regress 3D body shape and pose.
In this paper we demonstrate that self-similarity, and the resulting ambiguities in assigning pixel observations to the respective hands and their parts, is a major cause of the final 3D pose error.
Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable.
Ranked #2 on 3D Human Pose Estimation on 3DPW (using extra training data)
In this work, we propose a new training regularizer that aims to minimize the probabilistic expected training loss of a DNN subject to a generic Gaussian input.
Human motion is fundamental to understanding behavior.
Ranked #10 on 3D Human Pose Estimation on 3DPW (using extra training data)
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.
Ranked #5 on Multi-Person Pose Estimation on COCO