Reconstructing PASCAL VOC - Code

Reconstructing PASCAL VOC

Sara Vicente, Joao Carreira, Lourdes Agapito and Jorge Batista

Example 3D object reconstructions on some PASCAL VOC images:

S. Vicente*, J. Carreira*, L. Agapito and J. Batista. Reconstructing PASCAL VOC. [Oral]
In CVPR 2014. (* first two authors contributed equally) pdf slides talk .


We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs objects shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions. The visual hull sampling process attempts to intersect an object's projection cone with the cones of minimal subsets of other similar objects among those pictured from certain vantage points. We show that our method is able to produce recognizable per-object 3D reconstructions on one of the most challenging existing object-category detection datasets, PASCAL VOC. Our results may re-stimulate once popular geometry-oriented model-based recognition approaches.

A package with both MATLAB source code and synthetic test data is available here.
A package with just source code is available here.
A package with just the synthetic test data is available here. The synthetic dataset is described here.

The code has been tested on Linux 64 bits.