Meta-SR: A Magnification-Arbitrary Network for Super-Resolution

By Xuecai Hu, Haoyuan Mu, Xiangyu Zhang, Zilei Wang, Tien-Ping Tan. 2019

519 citations recorded by the source corpus.

Recent research on super-resolution has achieved greatsuccess due to the development of deep convolutional neu-ral networks (DCNNs). However, super-resolution of arbi-trary scale factor has been ignored for a long time. Mostprevious researchers regard super-resolution of differentscale factors as independent tasks. They train a specificmodel for each scale factor which is inefficient in comput-ing, and prior work only take the super-resolution of sev-eral integer scale factors into consideration. In this work,we propose a novel method called Meta-SR to firstly solvesuper-resolution of arbitrary scale factor (including non-integer scale factors) with a single model. In our Meta-SR,the Meta-Upscale Module is proposed to replace the tradi-tional upscale module. For arbitrary scale factor, the Meta-Upscale Module dynamically predicts the weights of the up-scale filters by taking the scale factor as input and use theseweights to generate the HR image of arbitrary size. For anylow-resolution image, our Meta-SR can continuously zoomin it with arbitrary scale factor by only using a single model.We evaluated the proposed method through extensive exper-iments on widely used benchmark datasets on single imagesuper-resolution. The experimental results show the superi-ority of our Meta-Upscale.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Dynamic Neural Networks: A Survey (2021, background): “I & S Image segmentation [32], [119], [136], [138], [140], [144], [146], [193], [194], [195], [196], [197], Image-to-image translation [198], Object detection [105], [106], [137], [138], [153], Semantic image synthesis [199], [200], [201], Computer Image denoising [202], Fine-grained classification ”
Unfolding the Alternating Optimization for Blind Super Resolution (2020, methodology): “From the arising of SRCNN [9], various DNNs [21, 40, 39, 10, 16, 18] have been proposed based on this setting.”
Implicit Diffusion Models for Continuous Super-Resolution (2023, unknown): “This section presents the IDM approach, a simple end-to-end framework with an effective scale-adaptive conditioning mechanism and an implicit diffusion process, to generate high-fidelity resolution-continuous outputs.”
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning (2019, background): “Recent works also applies meta learning on various tasks and achieves state-ofthe-art results in detection [47], super-resolution with arbitrary magnification [23] and instance segmentation [22].”
Learning Continuous Image Representation with Local Implicit Image Function (2020, methodology): “In Table 1 and Table 2, we show a quantitative comparison between our method and: i) EDSRbaseline, RDN: encoders with up-sampling modules, ii) MetaSR [15]: encoders with their meta decoder.”
PETR: Position Embedding Transformation for Multi-View 3D Object Detection (2022, methodology): “Analogously to Meta SR [17], the 3D position encoder can be formulated as: where ψ ( .”
Deep Learning for Image Super-Resolution: A Survey (2019, methodology): “Although this module needs to predict weights during inference, the execution time of the upsampling module only accounts for about 1% of the time of feature extraction [95].”
Residual Feature Aggregation Network for Image Super-Resolution (2020, background): “Following these pioneering works, many CNN-based methods have been proposed and achieved state-of-the-art results in SISR [15, 18, 40, 38, 3, 17, 7, 9, 39].”
Real-World Super-Resolution via Kernel Estimation and Noise Injection (2020, background): “Super-Resolution Recently, many Convolutional Neural Networks (CNN)-based SR networks [23, 30, 13, 14, 22, 31, 41] achieve strong performance on bicubic downsampling images.”
CARAFE: Content-Aware ReAssembly of FEatures (2019, background): “Within the realms of super-resolution and denoising, some other works [24, 14, 9] also explore using learnable kernels spatially in low-level vision.”
Deep Unfolding Network for Image Super-Resolution (2020, methodology): “Several methods have been proposed to tackle bicubic degradation with different scale factors via a single model, such as LapSR [30] with progressive upsampling, MDSR [36] with scales-speciﬁc branches, Meta-SR [23] with meta-upscale module.”
Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation (2021, methodology): “This idea has been applied to applications in different research fields such as few shot learning [27, 33], image segmentation [2, 36] and generative models [28, 18, 16], which is the focus of our paper.”
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, methodology): “These representations are used to upsample the images either to specific scales [37] or to arbitrary resolutions [10, 30, 58].”
Exploiting Aliasing for Manga Restoration (2021, methodology): “EDSR[14], SRGAN[12] and MetaSR[8] may generate blurry screentones while our method can restore the bitonal nature.”