To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information.
While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.
We consider the time-harmonic elastic wave scattering from a general (possibly anisotropic) inhomogeneous medium with an embedded impenetrable obstacle.
Analysis of PDEs 35B34, 74E99, 74J20
We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively.
However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result.
The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image.
Ranked #1 on Image Inpainting on Paris StreetView