Hierarchical image peeling: A flexible scale-space filtering framework

卷:235

Article

关键词: CONVOLUTIONAL FEATURES;    COLOR;    SEGMENTATION;    RETINEX;   

DOI  :  10.1016/j.cviu.2023.103769

来源: SCIE

【 摘 要 】

The importance of hierarchical image organization has been witnessed by a wide spectrum of applications in computer vision and graphics. Different from image segmentation with the spatial whole-part consideration, this work designs a modern framework for disassembling an image into a family of derived signals from a scale-space perspective. Specifically, we first formulate the goal of the hierarchical image organization problem. Then, by concerning desired properties, such as peeling hierarchy and structure preservation, we convert the original complex problem into a series of two-component separation sub-problems, significantly reducing the complexity. The proposed framework is flexible to be trained on both paired and unpaired data. A compact recurrent network, namely hierarchical image peeling net, is customized to efficiently and effectively fulfill the task, which is about 3.5Mb in size, and can handle 1080p images in more than 60 fps per recurrence on a GTX 2080Ti GPU, making it attractive for practical use. Both theoretical findings and experimental results are provided to demonstrate the efficacy of the proposed framework, reveal its superiority over other state-ofthe-art alternatives, and show its potential to various applicable scenarios. The codes have been made publicly available at https://github.com/ForawardStar/HIPe.

【 授权许可】

Free