Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings
This addresses the challenge of reliable 3D modeling from sketches for applications in CAD and design, representing an incremental improvement over prior optimization-based approaches.
The paper tackles the problem of automatic 3D reconstruction from single 2D line drawings by using deep neural networks to detect geometric constraints and predict initial depth values, significantly improving the success rate of optimization-based methods on a large CAD dataset.
In this paper, we revisit the long-standing problem of automatic reconstruction of 3D objects from single line drawings. Previous optimization-based methods can generate compact and accurate 3D models, but their success rates depend heavily on the ability to (i) identifying a sufficient set of true geometric constraints, and (ii) choosing a good initial value for the numerical optimization. In view of these challenges, we propose to train deep neural networks to detect pairwise relationships among geometric entities (i.e., edges) in the 3D object, and to predict initial depth value of the vertices. Our experiments on a large dataset of CAD models show that, by leveraging deep learning in a geometric constraint solving pipeline, the success rate of optimization-based 3D reconstruction can be significantly improved.