| Dense Object Reconstruction with Semantic
Priors Sid Yingze Bao*, Manmohan Chandraker^,
Yuanqing Lin^,
and Silvio Savarese*
* University of Michigan at Ann Arbor ^ NEC Lab, Cupertino, USA |
||
|
Sponsorship
 |
||
| What is it about? |
We present a dense
reconstruction approach that overcomes the drawbacks of traditional
multiview stereo by incorporating semantic information in the form of
learned category-level shape priors and object detection. Given
training data comprised of 3D scans and images of objects from various
viewpoints, we learn a prior comprised of a mean shape and a set of
weighted anchor points. The former captures the commonality of shapes
across the category, while the latter encodes similarities between
instances in the form of appearance and spatial consistency. We propose
robust algorithms to match anchor points across instances that enable
learning a mean shape for the category, even with large shape
variations across instances. We model the shape of an object instance
as a warped version of the category mean, along with instance-specific
details. Given multiple images of an unseen instance, we collate
information from 2D object detectors to align the structure from motion
point cloud with the mean shape, which is subsequently warped and
refined to approach the actual shape. Extensive experiments demonstrate
that our model is general enough to learn semantic priors for different
object categories, yet powerful enough to reconstruct individual shapes
with large variations. Qualitative and quantitative evaluations show
that our framework can produce more accurate reconstructions than alternative state-of-the-art multiview stereo systems. |
Update Sept 2013
|
| Papers and citations |
|
|
| Demo Videos | |
|