Convolutional Sketch Inversion
arXiv:1606.03073 · doi:10.1007/978-3-319-46604-0_56
Abstract
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.
References in corpus (5)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
- End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
Cited by in corpus (14)
- Deep Impression: Audiovisual Deep Residual Networks for Multimodal Apparent Personality Trait Recognition
- OmniArt: Multi-task Deep Learning for Artistic Data Analysis
- Deep Sketch-guided Cartoon Video Inbetweening
- Scribbler: Controlling Deep Image Synthesis with Sketch and Color
- TextureGAN: Controlling Deep Image Synthesis with Texture Patches
- Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
- PixelNN: Example-based Image Synthesis
- LUCSS: Language-based User-customized Colourization of Scene Sketches
- From A Glance to "Gotcha": Interactive Facial Image Retrieval with Progressive Relevance Feedback
- Attribute-Guided Sketch Generation
- DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
- Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
- Unified Style Transfer
- Forward Amortized Inference for Likelihood-Free Variational Marginalization