Self-Supervised Intrinsic Image Decomposition
Self-Supervised Intrinsic Image Decomposition
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Michael Janner;Jiajun Wu;Tejas D. Kulkarni;Ilker Yildirim;J. Tenenbaum
中科院分区：
文献类型：
--
作者：
Michael Janner;Jiajun Wu;Tejas D. Kulkarni;Ilker Yildirim;J. Tenenbaum
由于其固有的模糊性和训练数据的稀缺性，单个图像的内在分解是一项极具挑战性的任务。与传统的完全监督学习方法相比，在本文中，我们提出通过解释输入图像来学习内在图像分解。我们的模型，渲染内在网络（RIN），将图像分解管道连接在一起，该管道可以预测给定单个图像的反射率、形状和照明条件，并具有重组功能，这是一种学习的着色模型，用于根据内在图像预测重新组合原始输入。然后，我们的网络可以使用无监督重建误差作为附加信号来改进其中间表示。这使得大规模未标记数据在训练期间发挥作用，并且还能够将学到的知识转移到未见过的对象类别、照明条件和形状的图像中。大量的实验表明，我们的方法在内在图像分解和知识转移方面都表现良好。
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning intrinsic image decomposition by explaining the input image. Our model, the Rendered Intrinsics Network (RIN), joins together an image decomposition pipeline, which predicts reflectance, shape, and lighting conditions given a single image, with a recombination function, a learned shading model used to recompose the original input based off of intrinsic image predictions. Our network can then use unsupervised reconstruction error as an additional signal to improve its intermediate representations. This allows large-scale unlabeled data to be useful during training, and also enables transferring learned knowledge to images of unseen object categories, lighting conditions, and shapes. Extensive experiments demonstrate that our method performs well on both intrinsic image decomposition and knowledge transfer.