Year: 2024
Type: preprint
Abstract: Time cost is a major challenge in achieving high-quality pluralistic image completion. Recently, the Retentive Network (RetNet) in natural language processing offers a novel approach to this problem with its low-cost inference capabilities. Inspired by this, we apply RetNet to the pluralistic image completion task in computer vision. We present RetCompletion, a two-stage framework. In the first stage, we introduce Bi-RetNet, a bidirectional sequence information fusion model that integrates contextual information from images. During inference, we employ a unidirectional pixel-wise update strategy to restore consistent image structures, achieving both high reconstruction quality and fast inference speed. In the second stage, we use a CNN for low-resolution upsampling to enhance texture details. Experiments on ImageNet and CelebA-HQ demonstrate that our inference speed is 10$\times$ faster than ICT and 15$\times$ faster than RePaint. The proposed RetCompletion significantly improves inference speed and delivers strong performance.
Source: arXiv (Cornell University)
Authors: Cang, Yueyang, Hu, Pingge, Zhang, Xiaoteng, Wang, Xingtong, Liu, Yuhang, Shi, Li
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4403322391