Experiments show the PixelSR achieves state-of-the-art performance with shorter inference time in screen content super-resolution, and utilizes the properties of self-repetitiveness and redundancy in screen content to speed up inference without the loss of model performance.
Abstract
Screen content images are generally composed of texts and graphics. Compared to natural images, these man-made images contain a large quantity of sharp but repetitive structures. However, existing works in screen content super-resolution underutilize the special characteristics of screen content, leaving a large room to improve model performance and speed up. In this paper, we propose PixelSR, a simple yet effective method to improve super-resolution performance but with faster inference speed. To improve model performance, we classify pixels via pixel binning to compute content attention in the training phase. Specifically, after binning pixels into content-dependent groups, content attention is aggregated from pixel features within each group to introduce a content-dependent and non-local receptive field for every pixel. In the testing phase, we utilize the properties of self-repetitiveness and redundancy in screen content to speed up inference without the loss of model performance. We divide targeted high-resolution pixels into three types, which are unique pixels, repeated pixels, and background pixels for each test image. We conduct conventional network processing on unique pixels and cache their predictions in the on-the-fly lookup table. For repeated pixels which have appeared in unique pixels, we directly retrieve prediction results from the lookup table without network processing. For background pixels, we use the nearest neighbor algorithm to generate high-resolution pixels. The on-the-fly lookup table is cleaned and repeats the procedure above for the next test image. Experiments show our PixelSR achieves state-of-the-art performance with shorter inference time in screen content super-resolution.
With the development of electronic devices and contemporary coworking offices, remote offices such as online conferences and cloud desktops have become increasingly widespread. In remote offices, super-resolution is vital to break the limitation of restricted bandwidth for exhibiting screen content images (SCIs) in hig...
Jing-Yi Zhang, Meng-Han Zhou, Hao-Nan Jiang et al.· IEEE Transactions on Image P...· 0 citations
The proposed WMW-SAM, a Weighted Multi-Scale and Wavelet-Enhanced SAM, is designed to handle limitations of existing adaptation strategies for SOD, and develops the Weighted Multi-Scale Adapter (WMSA), which utilizes learnable weighting across multiple receptive fields to calibrate features of different scales.
MagnifiQ is introduced, an image restoration framework that progressively upscales and restores images across resolutions, e.g., from 1024x1024 to 4096x4096, and leverages a pre-trained text-to-image diffusion model such as SDXL and adapts it for more scalable high-resolution inference by replacing its original self-at...
M. Reddy, Yashesh Savani, Antoine Mercier et al.· 0 citations
Experiments show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions.
Xin Lin, Haodong Li, Zhi-Fei Zhang et al.· 1 citation
Aiming at the problems of large parameters and high computational complexity in deep learning-based image super-resolution networks, this paper proposes a lightweight super-resolution network that fuses multi-attention mechanism and Blueprint Separable Convolution (BSConv). BSConv is introduced to improve performance w...
A novel context-aware deep residual network with promotion gates, named as G-CASR network, for SISR, which requires only about 25% memory cost comparing with EDSR to improve the informative ability of extracted context information.
Xiao-Zhong Ji, Yi-Rui Wu, Tong Lu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.