Efficient Dense Point Cloud Object
Reconstruction Using Deformation Vector Fields
Abstract. Some existing CNN-based methods for single-view 3D object reconstruction represent a 3D object as either a 3D voxel occupancy
grid or multiple depth-mask image pairs. However, these representations
are inefficient since empty voxels or background pixels are wasteful. We
propose a novel approach that addresses this limitation by replacing
masks with “deformation-fields”. Given a single image at an arbitrary
viewpoint, a CNN predicts multiple surfaces, each in a canonical location relative to the object. Each surface comprises a depth-map and
corresponding deformation-field that ensures every pixel-depth pair in
the depth-map lies on the object surface. These surfaces are then fused
to form the full 3D shape. During training we use a combination of perview loss and multi-view losses. The novel multi-view loss encourages the
3D points back-projected from a particular view to be consistent across
views. Extensive experiments demonstrate the efficiency and efficacy of
our method on single-view 3D object reconstruction