RetCompletion:High-Speed Inference Image Completion with Retentive Network

Sábháilte in:
Sonraí bibleagrafaíochta
Foilsithe in:arXiv.org (Dec 4, 2024), p. n/a
Príomhchruthaitheoir: Cang, Yueyang
Rannpháirtithe: Hu, Pingge, Zhang, Xiaoteng, Wang, Xingtong, Liu, Yuhang, Shi, Li
Foilsithe / Cruthaithe:
Cornell University Library, arXiv.org
Ábhair:
Rochtain ar líne:Citation/Abstract
Full text outside of ProQuest
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

MARC

LEADER 00000nab a2200000uu 4500
001 3141232306
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3141232306 
045 0 |b d20241204 
100 1 |a Cang, Yueyang 
245 1 |a RetCompletion:High-Speed Inference Image Completion with Retentive Network 
260 |b Cornell University Library, arXiv.org  |c Dec 4, 2024 
513 |a Working Paper 
520 3 |a 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. 
653 |a Image restoration 
653 |a Data integration 
653 |a Computer vision 
653 |a Image resolution 
653 |a Image quality 
653 |a Image reconstruction 
653 |a Image enhancement 
653 |a Natural language processing 
653 |a Inference 
700 1 |a Hu, Pingge 
700 1 |a Zhang, Xiaoteng 
700 1 |a Wang, Xingtong 
700 1 |a Liu, Yuhang 
700 1 |a Shi, Li 
773 0 |t arXiv.org  |g (Dec 4, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3141232306/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2410.04056