Image Cropping Assisted By Modeling Inter-Patch Relations
基于斑块间关系建模的图像分割
パッチ間関係のモデリングに支援された画像トリミング
얼룩 블록 간 관계 기반 모델 링 이미지 재단
Recorte de imágenes basado en el modelado de la relación entre parches
Coupe d'image basée sur la modélisation des relations entre les parcelles
вырезка изображений на основе отношений между порциями
Tianpei Lian 连天培 ¹, Zhiguo Cao 曹治国 ¹, Hao Lu 陆昊 ¹, Zijin Wu ¹, Weicai Zhong ²
¹ School of Artificial Intelligence and Automation, Huazhong University of Science and Technology
华中科技大学 人工智能与自动化学院
² Huawei CBG Consumer Cloud Service Big Data Platform Dept
华为消费者云服务 大数据平台部
2021 IEEE International Conference on Image Processing (ICIP), 23 August 2021
Abstract
Image cropping is a common way to enhance the aesthetic quality of images. Huge industrial demand and the tediousness of image cropping make automatic image cropping a prosperous task. Existing works, however, face two difficulties: objects are easily truncated and key components of images are discarded by the model. The key to solving this problem is to understand the relations between different components of an image.
These relations break the limit of spatial distance and reflect the contextual information in images, which help the model decide whether to retain a component. Motivated by this, a patch-related graph module is proposed to model the relations between different patches of an image. The patch-related features are extracted by a graph convolution layer and then fused with the original local features by a proposed gated unit.
Moreover, a gradient layer is designed to embed the edge information in the input. The edge-prior input helps the model read the contents of images and reserve the main objects completely. Experimental results show that our model grasps the inter-patch relations well and performs competitively with other state-of-the-art approaches.