3D Human Body Reconstruction from a Single Image via Volumetric Regression
arXiv:1809.03770
Abstract
This paper proposes the use of an end-to-end Convolutional Neural Network for direct reconstruction of the 3D geometry of humans via volumetric regression. The proposed method does not require the fitting of a shape model and can be trained to work from a variety of input types, whether it be landmarks, images or segmentation masks. Additionally, non-visible parts, either self-occluded or otherwise, are still reconstructed, which is not the case with depth map regression. We present results that show that our method can handle both pose variation and detailed reconstruction given appropriate datasets for training.
arXiv commentAccepted to ECCV Workshops (PeopleCap) 2018
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Human pose estimation via Convolutional Part Heatmap Regression
- Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
- Synthesizing Training Images for Boosting Human 3D Pose Estimation
- Structured Prediction of 3D Human Pose with Deep Neural Networks