DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition
This work addresses the problem of intrinsic image decomposition for computer vision applications, offering a fully data-driven approach that simplifies architecture and training compared to recent methods, though it appears incremental in nature.
The authors tackled intrinsic image decomposition by developing a deep adversarial residual network that jointly estimates absolute albedo and shading from a single image, outperforming state-of-the-art deep algorithms on the MPI Sintel dataset.
We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components. Our contributions are based on a new fully convolutional neural network that estimates absolute albedo and shading jointly. Our solution relies on a single end-to-end deep sequence of residual blocks and a perceptually-motivated metric formed by two adversarially trained discriminators. As opposed to classical intrinsic image decomposition work, it is fully data-driven, hence does not require any physical priors like shading smoothness or albedo sparsity, nor does it rely on geometric information such as depth. Compared to recent deep learning techniques, we simplify the architecture, making it easier to build and train, and constrain it to generate a valid and reversible decomposition. We rediscuss and augment the set of quantitative metrics so as to account for the more challenging recovery of non scale-invariant quantities. We train and demonstrate our architecture on the publicly available MPI Sintel dataset and its intrinsic image decomposition, show attenuated overfitting issues and discuss generalizability to other data. Results show that our work outperforms the state of the art deep algorithms both on the qualitative and quantitative aspect.