Generalized Deep Image to Image Regression
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2016
- DOI:
- 10.48550/arXiv.1612.03268
- arXiv:
- arXiv:1612.03268
- Bibcode:
- 2016arXiv161203268S
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing
- E-Print:
- Submitted to CVPR on November 15th, 2016. Code will be made available soon