Search Results for author:
Found 4 papers, 1 papers with code
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
An increasing number of models require the control of the spectral norm of convolutional layers of a neural network.
Learning to Identify Physical Parameters from Video Using Differentiable Physics
Video prediction models often learn a latent representation of video which is encoded from input frames and decoded back into images.
Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction
Extracting the interpretable and physically meaningful parameters for such applications, however, requires solving an inverse problem in which a model function determined by these parameters needs to be fitted to the measured data.
Nonlinear Spectral Image Fusion
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
