Deep Image Harmonization with Learnable Augmentation
This work addresses the domain gap and data insufficiency in image harmonization for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of limited training data in image harmonization by introducing a learnable augmentation method, SycoNet, which enriches illumination diversity in small-scale datasets, leading to improved harmonization performance as demonstrated in comprehensive experiments.
The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination statistics of foregrounds of real images to produce synthetic composite images. However, different datasets have considerable domain gap and the performances on small-scale datasets are limited by insufficient training data. In this work, we explore learnable augmentation to enrich the illumination diversity of small-scale datasets for better harmonization performance. In particular, our designed SYthetic COmposite Network (SycoNet) takes in a real image with foreground mask and a random vector to learn suitable color transformation, which is applied to the foreground of this real image to produce a synthetic composite image. Comprehensive experiments demonstrate the effectiveness of our proposed learnable augmentation for image harmonization. The code of SycoNet is released at https://github.com/bcmi/SycoNet-Adaptive-Image-Harmonization.