-
Deep Networks for Image Super-Resolution with Sparse Prior
Deep learning techniques have been successfully applied in many areas of...
read it
-
Novel Super-Resolution Method Based on High Order Nonlocal-Means
Super-resolution without explicit sub-pixel motion estimation is a very ...
read it
-
Hierarchical Back Projection Network for Image Super-Resolution
Deep learning based single image super-resolution methods use a large nu...
read it
-
Deep Artifact-Free Residual Network for Single Image Super-Resolution
Recently, convolutional neural networks have shown promising performance...
read it
-
On the inverse Potts functional for single-image super-resolution problems
We consider a variational model for single-image super-resolution based ...
read it
-
Deep Unfolding Network for Image Super-Resolution
Learning-based single image super-resolution (SISR) methods are continuo...
read it
-
Deep Adaptive Inference Networks for Single Image Super-Resolution
Recent years have witnessed tremendous progress in single image super-re...
read it
Controlling Neural Networks via Energy Dissipation
The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques. Lately, many works have demonstrated that learning-based approaches with suitable network architectures even exhibit superior performance for the solution of (ill-posed) image reconstruction problems such as deblurring, super-resolution, or medical image reconstruction. The drawback of purely learning-based methods, however, is that they cannot provide provable guarantees for the trained network to follow a given data formation process during inference. In this work we propose energy dissipating networks that iteratively compute a descent direction with respect to a given cost function or energy at the currently estimated reconstruction. Therefore, an adaptive step size rule such as a line-search, along with a suitable number of iterations can guarantee the reconstruction to follow a given data formation model encoded in the energy to arbitrary precision, and hence control the model's behavior even during test time. We prove that under standard assumptions, descent using the direction predicted by the network converges (linearly) to the global minimum of the energy. We illustrate the effectiveness of the proposed approach in experiments on single image super resolution and computed tomography (CT) reconstruction, and further illustrate extensions to convex feasibility problems.
READ FULL TEXT
Comments
There are no comments yet.