Hierarchical Dynamic Image Harmonization
Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua, Meng, Weiqiang Wang, Huaxiong Li

TL;DR
This paper introduces HDNet, a hierarchical dynamic network for image harmonization that improves local and global visual consistency, reduces model size by over 80%, and achieves state-of-the-art results on iHarmony4.
Contribution
The paper proposes a novel hierarchical dynamic network with local and global modules for efficient image harmonization, significantly reducing model size while enhancing performance.
Findings
Reduces model parameters by over 80%
Achieves 4% higher PSNR than previous methods
Reduces MSE by 19% compared to state-of-the-art
Abstract
Image harmonization is a critical task in computer vision, which aims to adjust the foreground to make it compatible with the background. Recent works mainly focus on using global transformations (i.e., normalization and color curve rendering) to achieve visual consistency. However, these models ignore local visual consistency and their huge model sizes limit their harmonization ability on edge devices. In this paper, we propose a hierarchical dynamic network (HDNet) to adapt features from local to global view for better feature transformation in efficient image harmonization. Inspired by the success of various dynamic models, local dynamic (LD) module and mask-aware global dynamic (MGD) module are proposed in this paper. Specifically, LD matches local representations between the foreground and background regions based on semantic similarities, then adaptively adjust every foreground…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Advanced Vision and Imaging · Image and Signal Denoising Methods
MethodsConvolution
