paper-with-me

홈 › Papers

ITSRN++: Stronger and Better Implicit Transformer Network for Continuous Screen Content Image Super-Resolution

2022-10-17 · Sheng Shen, Huanjing Yue, Jingyu Yang, Kun Li

Nowadays, online screen sharing and remote cooperation are becoming ubiquitous. However, the screen content may be downsampled and compressed during transmission, while it may be displayed on large screens or the users would zoom in for detail observation at the receiver side. Therefore, developing a strong and effective screen content image (SCI) super-resolution (SR) method is demanded. We observe that the weight-sharing upsampler (such as deconvolution or pixel shuffle) could be harmful to sharp and thin edges in SCIs, and the fixed scale upsampler makes it inflexible to fit screens with various sizes. To solve this problem, we propose an implicit transformer network for continuous SCI SR (termed as ITSRN++). Specifically, we propose a modulation based transformer as the upsampler, which modulates the pixel features in discrete space via a periodic nonlinear function to generate features for continuous pixels. To enhance the extracted features, we further propose an enhanced transformer as the feature extraction backbone, where convolution and attention branches are utilized parallelly. Besides, we construct a large scale SCI2K dataset to facilitate the research on SCI SR. Experimental results on nine datasets demonstrate that the proposed method achieves state-of-the-art performance for SCI SR (outperforming SwinIR by 0.74 dB for x3 SR) and also works well for natural image SR. Our codes and dataset will be released upon the acceptance of this work.

📄 PDF Abstract BibTeX arXiv:2210.08812

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Implicit Transformer Network for Screen Content Image Continuous Super-Resolution

2021-12-12 · NeurIPS 2021 12 · Jingyu Yang, Sheng Shen, Huanjing Yue, Kun Li

Nowadays, there is an explosive growth of screen contents due to the wide application of screen sharing, remote cooperation, and online education. To match the limited terminal bandwidth, high-resolution (HR) screen cont…

Super-Resolution

Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent

2023-02-02 · Avrajit Ghosh, He Lyu, Xitong Zhang, Rongrong Wang

It is well known that the finite step-size ($h$) in Gradient Descent (GD) implicitly regularizes solutions to flatter minima. A natural question to ask is "Does the momentum parameter $\beta$ play a role in implicit regu…

Dynamical Implicit Neural Representations

2025-11-26 · Yesom Park, Kelvin Kan, Thomas Flynn, Yi Huang 외 arxiv

Implicit Neural Representations (INRs) provide a powerful continuous framework for modeling complex visual and geometric signals, but spectral bias remains a fundamental challenge, limiting their ability to capture high-…

Language Models Are Implicitly Continuous

2025-04-04 · Samuele Marro, Davide Evangelista, X. Angelo Huang, Emanuele La Malfa 외

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that …

Language Modelling

Stronger Normalization-Free Transformers

2025-12-11 · Mingzhi Chen, Taiming Lu, Jiachen Zhu, Mingjie Sun 외 arxiv

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wis…