Abstract

3D reconstruction from a single image is a classical problem in computer vision. However, it still poses great challenges for the reconstruction of daily-use objects with irregular1 shapes. In this paper, we propose to learn 3D reconstruction knowledge from informally captured2 RGB-D images, which will probably be ubiquitously used in daily life. The learning of 3D reconstruction is defifined as a category modeling problem, in which a model for each category is trained to encode category-specifific knowledge for 3D reconstruction. The category model estimates the pixellevel 3D structure of an object from its 2D appearance, by taking into account considerable variations in rotation, 3D structure, and texture. Learning 3D reconstruction from ubiquitous RGB-D images creates a new set of challenges. Experimental results have demonstrated the effectiveness of the proposed approach.