RetCompletion:High-Speed Inference Image Completion with Retentive Network

保存先:

書誌詳細
出版年:	arXiv.org (Dec 4, 2024), p. n/a
第一著者:	Cang, Yueyang
その他の著者:	Hu, Pingge, Zhang, Xiaoteng, Wang, Xingtong, Liu, Yuhang, Shi, Li
出版事項:	Cornell University Library, arXiv.org
主題:	Image restoration Data integration Computer vision Image resolution Image quality Image reconstruction Image enhancement Natural language processing Inference
オンライン･アクセス:	Citation/Abstract Full text outside of ProQuest
タグ:	タグ追加タグなし, このレコードへの初めてのタグを付けませんか!

その他の書誌記述
抄録:	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.
ISSN:	2331-8422
ソース:	Engineering Database