1

Multi-View Neural Human Rendering

We present an end-to-end Neural Human Renderer (NHR) for dynamic human captures under the multi-view setting. NHR adopts PointNet++ for feature extraction (FE) to enable robust 3D correspondence matching on low quality, dynamic 3D reconstructions. To …

Multiview Vehicle Tracking by Graph Matching Model.

In this work, we propose a novel and flexible vehicle tracking framework, which formulates matching problem as a graph matching problem and solve it from the bottom up. In our framework, many restrictions can be added into the graph uniformly and …

RGBD based gaze estimation via multi-task CNN

This paper tackles RGBD based gaze estimation with Convolutional Neural Networks (CNNs). Specifically, we propose to decompose gaze point estimation into eyeball pose, head pose, and 3D eye position estimation. Compared with RGB image-based gaze …

4D Human Body Correspondences from Panoramic Depth Maps

The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex correspondences. …