Neural 3D Mesh Renderer

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 3907 - 3916
• Main Authors: Kato, Hiroharu, Ushiku, Yoshitaka, Harada, Tatsuya
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Face; Image color analysis; Neural networks; Rendering (computer graphics); Solid modeling; Three-dimensional displays; Two dimensional displays
• DOI: 10.1109/CVPR.2018.00411

For modeling the 3D world behind 2D images, which 3D representation is most appropriate? A polygon mesh is a promising candidate for its compactness and geometric properties. However, it is not straightforward to model a polygon mesh from 2D images using neural networks because the conversion from a mesh to an image, or rendering, involves a discrete operation called rasterization, which prevents back-propagation. Therefore, in this work, we propose an approximate gradient for rasterization that enables the integration of rendering into neural networks. Using this renderer, we perform single-image 3D mesh reconstruction with silhouette image supervision and our system outperforms the existing voxel-based approach. Additionally, we perform gradient-based 3D mesh editing operations, such as 2D-to-3D style transfer and 3D DeepDream, with 2D supervision for the first time. These applications demonstrate the potential of the integration of a mesh renderer into neural networks and the effectiveness of our proposed renderer.