Category-Specific Object Reconstruction from a Single Image
This addresses the challenge of 3D reconstruction from limited 2D data for computer vision applications, but it appears incremental as it builds on existing datasets and methods.
The paper tackles the problem of reconstructing 3D objects from a single image in realistic scenes, using an automated pipeline that outputs 3D surfaces for rigid categories, and shows encouraging results on the PASCAL VOC dataset.
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.