Image-Based Synthesis and Re-synthesis of Viewpoints Guided by 3D Models
Computer Vision and Pattern Recognition(2014)
摘要
We propose a technique to use the structural informa- tion extracted from a set of 3D models of an object class to improve novel-view synthesis for images showing unknown instances of this class. These novel views can be used to \"amplify\" training image collections that typically contain only a low number of views or lack certain classes of views entirely (e. g. top views). We extract the correlation of position, normal, re- flectance and appearance from computer-generated images of a few exemplars and use this information to infer new appearance for new instances. We show that our approach can improve performance of state-of-the-art detectors using real-world training data. Additional applications include guided versions of inpainting, 2D-to-3D conversion, super- resolution and non-local smoothing.
更多查看译文
关键词
image resolution,learning (artificial intelligence),2D-to-3D conversion,3D models,computer-generated images,nonlocal smoothing,object class,real-world training data,structural information extraction,super resolution,training image collections,computer graphics,computer vision,image-based rendering,object detection,synthetic training data
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络