Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
2015 IEEE International Conference on Computer Vision (ICCV)(2015)
摘要
We introduce a new approach to intrinsic image decomposition, the task of decomposing a single image into albedo and shading components. Our strategy, which we term direct intrinsics, is to learn a convolutional neural network (CNN) that directly predicts output albedo and shading channels from an input RGB image patch. Direct intrinsics is a departure from classical techniques for intrinsic image decomposition, which typically rely on physically-motivated priors and graph-based inference algorithms. The large-scale synthetic ground-truth of the MPI Sintel dataset plays a key role in training direct intrinsics. We demonstrate results on both the synthetic images of Sintel and the real images of the classic MIT intrinsic image dataset. On Sintel, direct intrinsics, using only RGB input, outperforms all prior work, including methods that rely on RGB+Depth input. Direct intrinsics also generalizes across modalities; it produces quite reasonable decompositions on the real images of the MIT dataset. Our results indicate that the marriage of CNNs with synthetic training data may be a powerful new technique for tackling classic problems in computer vision.
更多查看译文
关键词
direct intrinsics,learning Albedo-shading decomposition,convolutional regression,intrinsic image decomposition,convolutional neural network,CNN,shading channels,RGB image patch,graph based inference algorithms,MPI Sintel dataset,RGB input,reasonable decompositions,computer vision
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络