High-Resolution Image Harmonization via Collaborative Dual Transformations
Preprint
Abstract
Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background. High-resolution image harmonization is in high demand, but still remains unexplored. Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context. Recent deep learning methods learn the dense pixel-to-pixel transformation which could generate harmonious outputs, but are highly constrained in low resolution. In this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end network. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution benchmark dataset and our created high-resolution real composite images demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness. Our used datasets can be found in https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images2019
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs2018
- RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation2017
- Deep Image Harmonization2017
- A Comparative Study for Single Image Blind Deblurring2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Error-Tolerant Image CompositingInternational Journal of Computer Vision, 2012
- Medical image enhancement based on modified lut-mapping derivative and multi-scale layer contrast modification2011
- Image Denoising with Shrinkage and Redundant Representations2006
- Color transfer between imagesIEEE Computer Graphics and Applications, 2001