Hair surface reconstruction from wide-baseline camera arrays

摘要

The subject disclosure is directed towards reconstructing an approximate hair surface using refinement of hair strands. Hair strands are first extracted from 2D images of a camera array, and projected onto a 3D visual hull. The 3D positions of these strands are refined by optimizing an objective function that takes into account orientation consistency, a visual hull constraint and/or smoothness constraints defined at the strand, wisp and/or global levels.

主权项

1. A method implemented at least in part on at least one processor, comprising, processing a plurality of images obtained from a wide baseline camera array into output rendering data that includes reconstructed hair data, including processing the images into per-camera orientation maps, extracting strand data from the orientation maps, projecting the strand data onto a visual hull, and refining the strand data including optimizing projected orientation consistency using one or more constraints.