Deep Network Interpolation for Continuous Imagery Effect Transition

Abstract

Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect. However, the large variety of user flavors motivates the possibility of continuous transition among different output effects. Unlike existing methods that require a specific design to achieve one particular transition (e.g., style transfer), we propose a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer. Specifically, our method, namely Deep Network Interpolation (DNI), applies linear interpolation in the parameter space of two or more correlated networks. A smooth control of imagery effects can be achieved by tweaking the interpolation coefficients. In addition to DNI and its broad applications, we also investigate the mechanism of network interpolation from the perspective of learned filters.

Technical report

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Residual Learning for Image Recognition
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• A Learned Representation For Artistic Style
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Multimodal Unsupervised Image-to-Image Translation
• Convergent Learning: Do different neural networks learn the same representations?
• Learning Deep CNN Denoiser Prior for Image Restoration
• Deep Learning Face Attributes in the Wild
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
• Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring