3D Pose Estimation
105 papers with code • 6 benchmarks • 23 datasets
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels.
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.
Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.
We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images.
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature.
In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.