Convolutional Sketch Inversion
This work addresses the need for realistic face image synthesis from sketches, with applications in fine arts and forensic arts, but it is incremental as it builds on existing deep learning techniques.
The paper tackles the problem of inverting face sketches to synthesize photorealistic face images, achieving state-of-the-art results on both computer-generated and hand-drawn sketches by leveraging deep neural networks and a new semi-simulated dataset.
In this paper, we use deep neural networks for inverting face sketches to synthesize photorealistic face images. We first construct a semi-simulated dataset containing a very large number of computer-generated face sketches with different styles and corresponding face images by expanding existing unconstrained face data sets. We then train models achieving state-of-the-art results on both computer-generated sketches and hand-drawn sketches by leveraging recent advances in deep learning such as batch normalization, deep residual learning, perceptual losses and stochastic optimization in combination with our new dataset. We finally demonstrate potential applications of our models in fine arts and forensic arts. In contrast to existing patch-based approaches, our deep-neural-network-based approach can be used for synthesizing photorealistic face images by inverting face sketches in the wild.