Helmholtz stereovision methods are limited to binocular stereovision or depth maps reconstruction. In this paper, we extend these methods to recover the full 3D shape of the object...
This paper introduces a feature based method for the fast generation of sparse 3D point clouds from multiple images with known pose. We extract sub-pixel edge elements (2D positio...
This paper addresses the “boundary ownership” problem,
also known as the figure/ground assignment problem.
Estimating boundary ownerships is a key step in perceptual
organiz...
In cross-modal inference, we estimate complete fields from noisy and missing observations of one sensory modality using structure found in another sensory modality. This inference...
S. Ravela, Antonio B. Torralba, William T. Freeman
We present a compact, image-based representation for threedimensional objects with complex shapes that can be rendered with correct perspective from arbitrary viewpoints using a l...