Shape from Shading through Shape Evolution
arXiv:1712.02961
Abstract
In this paper, we address the shape-from-shading problem by training deep networks with synthetic images. Unlike conventional approaches that combine deep learning and synthetic imagery, we propose an approach that does not need any external shape dataset to render synthetic images. Our approach consists of two synergistic processes: the evolution of complex shapes from simple primitives, and the training of a deep network for shape-from-shading. The evolution generates better shapes guided by the network training, while the training improves by using the evolved shapes. We show that our approach achieves state-of-the-art performance on a shape-from-shading benchmark.
References in corpus (10)
- Stacked Hourglass Networks for Human Pose Estimation
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Playing for Data: Ground Truth from Computer Games
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- A Large Dataset of Object Scans
- 3D ShapeNets: A Deep Representation for Volumetric Shapes
- From Shading to Local Shape
- Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
- Designing Deep Networks for Surface Normal Estimation