Category-specific object reconstruction from a single image
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1966-1974
- https://doi.org/10.1109/cvpr.2015.7298807
Abstract
Object reconstruction from a single image - in the wild - is a problem where we can make progress and get meaningful results today. This is the main message of this paper, which introduces an automated pipeline with pixels as inputs and 3D surfaces of various rigid categories as outputs in images of realistic scenes. At the core of our approach are deformable 3D models that can be learned from 2D annotations available in existing object detection datasets, that can be driven by noisy automatic object segmentations and which we complement with a bottom-up module for recovering high-frequency shape details. We perform a comprehensive quantitative analysis and ablation study of our approach using the recently introduced PASCAL 3D+ dataset and show very encouraging automatic reconstructions on PASCAL VOC.Keywords
Other Versions
This publication has 27 references indexed in Scilit:
- Detailed 3D Representations for Object Recognition and ModelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- How Little Do We Need for 3-D Shape Perception?Perception, 2011
- Blocks World Revisited: Image Understanding Using Qualitative Geometry and MechanicsLecture Notes in Computer Science, 2010
- Inferring 3D Shapes and Deformations from Single ViewsLecture Notes in Computer Science, 2010
- A Surface Deformation Framework for 3D Shape RecoveryLecture Notes in Computer Science, 2006
- SCAPEACM Transactions on Graphics, 2005
- Silhouette and stereo fusion for 3D object modelingComputer Vision and Image Understanding, 2004
- Face recognition based on fitting a 3D morphable modelIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- The visual hull concept for silhouette-based image understandingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Description and recognition of curved objectsArtificial Intelligence, 1977