Shape from Shading through Shape Evolution
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(2017)
摘要
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.
更多查看译文
关键词
shape evolution,shape-from-shading problem,training deep networks,synthetic images,conventional approaches,deep learning,synthetic imagery,external shape dataset,synergistic processes,complex shapes,simple primitives,deep network,network training,evolved shapes,shape-from-shading benchmark
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络