Paper Info
Title
Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations
Abstract
This paper presents a Generative prior ReciprocAted Invertible rescaling Network (GRAIN) for generating faithful high-resolution (HR) images from low-resolution (LR) invertible images with an extreme upscaling factor (64×). Previous researches have leveraged the prior knowledge of a pretrained GAN model to generate high-quality upscaling results. However, they fail to produce pixel-accurate results due to the highly ambiguous extreme mapping process. We remedy this problem by introducing a reciprocated invertible image rescaling process, in which high-resolution information can be delicately embedded into an invertible low-resolution image and generative prior for a faithful HR reconstruction. In particular, the invertible LR features not only carry significant HR semantics, but also are trained to predict scale-specific latent codes, yielding a preferable utilization of generative features. On the other hand, the enhanced generative prior is re-injected to the rescaling process, compensating the lost details of the invertible rescaling. Our reciprocal mechanism perfectly integrates the advantages of invertible encoding and generative prior, leading to the first feasible extreme rescaling solution. Extensive experiments demonstrate superior performance against state-of-the-art upscaling methods. Code is available at https://github.com/cszzx/GRAIN.
Year
DOI
Venue
2022
10.1109/CVPR52688.2022.00562
IEEE Conference on Computer Vision and Pattern Recognition
Keywords
DocType
Volume
Low-level vision, Face and gestures, Image and video synthesis and generation
Conference
2022
Issue
Citations 
PageRank 
1
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Zhixuan Zhong100.34
Liangyu Chai200.68
Yang Zhou300.34
Bailin Deng400.34
Jia Pan500.68
Shengfeng He640633.19