Image Style Transfer using Convolutional Neural Networks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Cellpose: a generalist algorithm for cellular segmentation (2020, methodology): “In-between the downsampling and upsampling we computed an image style [21], defined as the global average pool of each feature map [22], resulting in a 256-dimensional feature vector for each image.”
Enhancing Underwater Imagery Using Generative Adversarial Networks (2018, background): “Recent work in generative models, speciﬁcally GANs, have shown great success in areas such as inpainting [24], style transfer [8], and image-to-image translation [14, 35].”
Deep Generative Models in Engineering Design: A Review (2021, methodology): “Since reconstruction often involves mimicking existing microstructures, several papers have applied style transfer [119,120] to the problem as part of a DGM architecture.”
Arbitrary Style Transfer With Style-Attentional Networks (2018, methodology): “[5] showed that the correlation between features extracted from a pre-trained deep neural network can capture the style patterns well.”
Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations (2018, background): “Style transfer [15] provides a synthetic way to test style robustness by algorithmically and artiﬁcially recomposing the image in the style of another image.”
Selective clustering for representative paintings selection (2019, background): “Previous image style transfer works only focus on expressing the artistic style of a specific painting [10, 25].”