Object-Driven Multi-Layer Scene Decomposition From a Single Image
Object-Driven Multi-Layer Scene Decomposition From a Single Image
复制标题
DOI：
10.1109/iccv.2019.00547
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Helisa Dhamo;N. Navab;Federico Tombari
中科院分区：
文献类型：
--
作者：
Helisa Dhamo;N. Navab;Federico Tombari
我们提出了一种方法，解决了预测图像可见内容背后的颜色和深度的挑战。我们的方法旨在从单个RGB输入建立分层深度图像(LDI)，这是一种将场景按层排列的有效表示，包括最初被遮挡的区域。与以前的工作不同，我们启用了一种自适应的层数方案，并结合了语义编码来更好地产生部分遮挡对象的幻觉。此外，我们的方法是对象驱动的，这特别提高了对被遮挡的中间对象的准确性。该框架由两个步骤组成。首先，我们在估计场景布局的同时，分别完成每个对象的颜色和深度。其次，我们基于回归层重建场景，并强制重组后的图像与原始输入的结构相似。学习的表示法使各种应用得以实现，例如3D摄影和减弱的真实感，所有这些都来自一幅RGB图像。
We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation that arranges the scene in layers, including originally occluded regions. Unlike previous work, we enable an adaptive scheme for the number of layers and incorporate semantic encoding for better hallucination of partly occluded objects. Additionally, our approach is object-driven, which especially boosts the accuracy for the occluded intermediate objects. The framework consists of two steps. First, we individually complete each object in terms of color and depth, while estimating the scene layout. Second, we rebuild the scene based on the regressed layers and enforce the recomposed image to resemble the structure of the original input. The learned representation enables various applications, such as 3D photography and diminished reality, all from a single RGB image.