Real-Time User-Guided Image Colorization with Learned Deep Priors

Abstract

We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN). Rather than using hand-defined rules, the network propagates user edits by fusing low-level cues along with high-level semantic information, learned from large-scale data. We train on a million images, with simulated user inputs. To guide the user towards efficient input selection, the system recommends likely colors based on the input image and current user inputs. The colorization is performed in a single feed-forward pass, enabling real-time use. Even with randomly simulated user inputs, we show that the proposed system helps novice users quickly create realistic colorizations, and offers large improvements in colorization quality with just a minute of use. In addition, we demonstrate that the framework can incorporate other user "hints" to the desired colorization, showing an application to color histogram transfer. Our code and models are available at https://richzhang.github.io/ideepcolor.

arXiv commentAccepted to SIGGRAPH 2017. Project page: https://richzhang.github.io/ideepcolor

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Holistically-Nested Edge Detection
• Generative Visual Manipulation on the Natural Image Manifold
• Learning Representations for Automatic Colorization
• Outline Colorization through Tandem Adversarial Networks
• Deep Interactive Object Selection
• Learning a Discriminative Model for the Perception of Realism in Composite Images
• A 4D Light-Field Dataset and CNN Architectures for Material Recognition

Cited by in corpus (16)

• Toward Multimodal Image-to-Image Translation
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2
• RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding
• Deep Exemplar-based Video Colorization
• VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
• End-to-End Conditional GAN-based Architectures for Image Colourisation
• Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning
• FlowChroma -- A Deep Recurrent Neural Network for Video Colorization
• GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
• Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies
• Color Sails: Discrete-Continuous Palettes for Deep Color Exploration
• ViT-Inception-GAN for Image Colourising
• A Survey on Adversarial Image Synthesis
• Semantic-driven Colorization
• TUCaN: Progressively Teaching Colourisation to Capsules