Stochastic refinement of the visual hull to satisfy photometric and silhouette consistency constraints

Abstract

Abstract

Model-based human shape reconstruction from multiple views

“…Objectcentred reconstruction has been used to improve reconstructed scene models of people in model-enhanced stereo [13] where an initial surface reconstruc-tion is used to restrict the search range to refine stereo correspondence. More recently techniques have been presented to refine a robust initial estimate of shape derived from silhouettes by incorporating stereo and photo-consistency from multiple views [11,16,17]. These techniques combine shape cues for robust reconstruction without the requirement for a prior surface model but provide no structure for animation synthesis.…”

3-D studio production of animated actor models

“…The quality of reconstructed texture mapped models is limited by the visual-hull which only reconstructs an approximate, locally convex, representation of the surface resulting in coarse geometry and visual artefacts due to incorrect alignment of overlapping images in texture map generation. Stereo surface has been used to improve reconstruction of surface detail [8,20,25]. Plaenkers and Fua [20] used implicit surface models to simultaneously reconstruct shape and movement from stereo point clouds.…”

Reconstructing Relief Surfaces

“…Previous mesh-based multi-view stereo techniques operate by iteratively evolving an initial mesh until it best fits a set of images [14,26], or depth maps [10]. Representing finely detailed geometry is difficult for such methods due to the need to manage large and complex meshes.…”