Model-based Outdoor Performance Capture

Abstract

We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and nonrigid surface shape refinement. Our method fits the template to unsegmented video frames in two stages - first, the coarse skeletal pose is estimated, and subsequently non-rigid surface shape and body pose are jointly refined. Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection. We obtain reconstructions of much higher quality in outdoor settings than existing methods, and show that we are on par with state-of-the-art methods on indoor scenes for which they were designed

3DV 2016

References in corpus (6)

• Fast and Robust Hand Tracking Using Detection-Guided Optimization
• Building Statistical Shape Spaces for 3D Human Modeling
• General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
• Temporally coherent 4D reconstruction of complex dynamic scenes
• Efficient Multi-view Performance Capture of Fine-Scale Surface Detail
• General Dynamic Scene Reconstruction from Multiple View Video

Cited by in corpus (5)

• MonoPerfCap: Human Performance Capture from Monocular Video
• Video Based Reconstruction of 3D People Models
• Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
• Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
• Robust 3D Human Motion Reconstruction Via Dynamic Template Construction