Compact Model Representation for 3D Reconstruction
This addresses the challenge of single-image 3D reconstruction for computer vision applications, but it appears incremental as it builds on prior knowledge of CAD models.
The paper tackles the problem of 3D reconstruction from a single 2D image by compactly representing millions of CAD models to generalize to unseen objects with fine geometry, achieving impressive dense and realistic reconstructions as demonstrated through comprehensive analysis.
3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image. It is well known however that only one image cannot provide enough information for such a reconstruction. A prior knowledge that has been entertained are 3D CAD models due to its online ubiquity. A fundamental question is how to compactly represent millions of CAD models while allowing generalization to new unseen objects with fine-scaled geometry. We introduce an approach to compactly represent a 3D mesh. Our method first selects a 3D model from a graph structure by using a novel free-form deformation FFD 3D-2D registration, and then the selected 3D model is refined to best fit the image silhouette. We perform a comprehensive quantitative and qualitative analysis that demonstrates impressive dense and realistic 3D reconstruction from single images.