3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
This addresses the problem of creating detailed 3D models from sketches for applications in design and graphics, representing an incremental improvement over prior techniques.
The paper tackles 3D shape reconstruction from 2D sketches using a multi-view convolutional network, resulting in more faithful reconstructions with higher surface resolution and better preservation of topology compared to existing methods like volumetric networks.
We propose a method for reconstructing 3D shapes from 2D sketches in the form of line drawings. Our method takes as input a single sketch, or multiple sketches, and outputs a dense point cloud representing a 3D reconstruction of the input sketch(es). The point cloud is then converted into a polygon mesh. At the heart of our method lies a deep, encoder-decoder network. The encoder converts the sketch into a compact representation encoding shape information. The decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints. The multi-view maps are then consolidated into a 3D point cloud by solving an optimization problem that fuses depth and normals across all viewpoints. Based on our experiments, compared to other methods, such as volumetric networks, our architecture offers several advantages, including more faithful reconstruction, higher output surface resolution, better preservation of topology and shape structure.