Space Carving MVD Sequences for Modeling Natural 3D Scenes

Youssef Alj (1, 2) , Guillaume Boisson (1) , Philippe Bordes (1) , Muriel Pressigout (2) , Luce Morin (2)

1 Technicolor [Cesson Sévigné]
2 IETR - Institut d'Electronique et de Télécommunications de Rennes

This paper presents a 3D modeling system designed for Multi-view Video plus Depth (MVD) sequences. The aim is to remove redundancy in both texture and depth information present in the MVD data. To this end, a volumetric framework is employed in order to merge the input depth maps. Hereby a variant of the Space Carving algorithm is proposed. Voxels are iteratively carved by ray-casting from each view, until the 3D model be geometrically consistent with every input depth map. A surface mesh is then extracted from this volumetric representation thanks to the Marching Cubes algorithm. Subsequently, to address the issue of texture modeling, a new algorithm for multi-texturing the resulting surface is presented. This algorithm selects from the set of input images the best texture candidate to map a given mesh triangle. The best texture is chosen according to a photoconsistency metric. Tests and results are provided using still images from usual MVD test-sequences.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Youssef Alj, Guillaume Boisson, Philippe Bordes, Muriel Pressigout, Luce Morin. Space Carving MVD Sequences for Modeling Natural 3D Scenes. Three-Dimensional Image Processing (3DIP) and Applications II, Jan 2012, United States. pp.1-8. ⟨hal-00751443⟩