This paper introduces a region-of-interest visual hull refinement technique, based on flexible voxel grids for volumetric visual hull reconstructions. Region-of-interest refinemen...
We study the use of neural network algorithms in surface reconstruction from an unorganized point cloud, and meshing of an implicit surface. We found that for such applications, t...
Ioannis P. Ivrissimtzis, Won-Ki Jeong, Hans-Peter ...
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is...
Michael Goesele, Noah Snavely, Brian Curless, Hugu...
This paper proposes a method to automatically detect and reconstruct planar surfaces for immediate use in AR tasks. Traditional methods for plane detection are typically based on ...