|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed.
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance.
The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input.
The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image.
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
In this paper, we study the effectiveness of conditioning GANs by adding an explicit regularization term to enforce pixel-wise conditions when very few pixel values are provided.