Reconstructing PASCAL VOC
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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 object 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 convincing 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.Keywords
This publication has 24 references indexed in Scilit:
- Boundary Cues for 3D Object Shape RecoveryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Semantic contours from inverse detectorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Representations and Techniques for 3D Object Recognition and Scene InterpretationSynthesis Lectures on Artificial Intelligence and Machine Learning, 2011
- Finding nemo: Deformable object class modelling using curve matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Estimating 3D shape from degenerate sequences with missing dataComputer Vision and Image Understanding, 2009
- Object Recognition in the Geometric Era: A RetrospectiveLecture Notes in Computer Science, 2006
- Multiple View Geometry in Computer VisionPublished by Cambridge University Press (CUP) ,2004
- Inferring 3D structure with a statistical image-based shape modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The visual hull concept for silhouette-based image understandingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994