Generalized Deep Image to Image Regression
This work addresses the need for a versatile deep learning model for various image processing tasks, though it is incremental as it builds on existing convolutional neural network architectures.
The authors tackled the problem of creating a generic image-to-image regressor by proposing the Recursively Branched Deconvolutional Network (RBDN), which achieved comparable results to state-of-the-art methods on relighting, denoising, and colorization tasks without task-specific modifications.
We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture: the Recursively Branched Deconvolutional Network (RBDN) develops a cheap multi-context image representation very early on using an efficient recursive branching scheme with extensive parameter sharing and learnable upsampling. This multi-context representation is subjected to a highly non-linear locality preserving transformation by the remainder of our network comprising of a series of convolutions/deconvolutions without any spatial downsampling. The RBDN architecture is fully convolutional and can handle variable sized images during inference. We provide qualitative/quantitative results on $3$ diverse tasks: relighting, denoising and colorization and show that our proposed RBDN architecture obtains comparable results to the state-of-the-art on each of these tasks when used off-the-shelf without any post processing or task-specific architectural modifications.