论文标题
图像协调的前景感知语义表示
Foreground-aware Semantic Representations for Image Harmonization
论文作者
论文摘要
图像协调是照片编辑中的重要一步，可以通过调整前景的外观以使其与背景兼容，以实现复合图像中的视觉一致性。以前的协调复合材料的方法是基于从头开始对编码器 - 码头网络的培训，这使得神经网络学习对象的高级表示，这使其具有挑战性。我们提出了一种新颖的体系结构，以利用预先训练的分类网络学到的高级特征的空间。我们创建模型作为现有的编码器架构和预训练的前景高分辨率网络的结合。我们广泛评估了现有图像协调基准的提议方法，并根据MSE和PSNR指标建立了新的最新方法。代码和训练有素的模型可在\ url {https://github.com/saic-vul/image_harmonization}上获得。
Image harmonization is an important step in photo editing to achieve visual consistency in composite images by adjusting the appearances of foreground to make it compatible with background. Previous approaches to harmonize composites are based on training of encoder-decoder networks from scratch, which makes it challenging for a neural network to learn a high-level representation of objects. We propose a novel architecture to utilize the space of high-level features learned by a pre-trained classification network. We create our models as a combination of existing encoder-decoder architectures and a pre-trained foreground-aware deep high-resolution network. We extensively evaluate the proposed method on existing image harmonization benchmark and set up a new state-of-the-art in terms of MSE and PSNR metrics. The code and trained models are available at \url{https://github.com/saic-vul/image_harmonization}.
