B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution
Screen content images (SCIs) include many informative components, e.g., texts and graphics. Such content creates sharp edges or homogeneous areas, making a pixel distribution of SCI different from the natural image. Therefore, we need to properly handle the edges and textures to minimize information distortion of the contents when a display device's resolution differs from SCIs. To achieve this goal, we propose an implicit neural representation using B-splines for screen content image super-resolution (SCI SR) with arbitrary scales. Our method extracts scaling, translating, and smoothing parameters of B-splines. The followed multi-layer perceptron (MLP) uses the estimated B-splines to recover high-resolution SCI. Our network outperforms both a transformer-based reconstruction and an implicit Fourier representation method in almost upscaling factor, thanks to the positive constraint and compact support of the B-spline basis. Moreover, our SR results are recognized as correct text letters with the highest confidence by a pre-trained scene text recognition network. Source code is available at https://github.com/ByeongHyunPak/btc.
Code (1)
Tasks
Image Super-ResolutionScene Text RecognitionSuper-ResolutionSimilar Papers 제목 키워드 기반
Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation
While existing implicit neural network-based image unwarping methods perform well on natural images, they struggle to handle screen content images (SCIs), which often contain large geometric distortions, text, symbols, a…
Estimation of Latent Group Structures in Time-Varying Panel Data Models
We introduce a panel data model where coefficients vary both over time and the cross-section. Slope coefficients change smoothly over time and follow a latent group structure, being homogeneous within but heterogeneous a…
Deep neural networks for smooth approximation of physics with higher order and continuity B-spline base functions
This paper deals with the following important research question. Traditionally, the neural network employs non-linear activation functions concatenated with linear operators to approximate a given physical phenomenon. Th…
UKAN: Unbound Kolmogorov-Arnold Network Accompanied with Accelerated Library
In this work, we present a GPU-accelerated library for the underlying components of Kolmogorov-Arnold Networks (KANs), along with an algorithm to eliminate bounded grids in KANs. The GPU-accelerated library reduces the c…
BenchmarkingComputational EfficiencyGPUKolmogorov-Arnold NetworksTrainable Spline Representations for Physics-Informed Learning
This work introduces Physics-Informed Splines (PI-Splines), a structured spline-based architecture for physics-informed learning. Instead of representing the solution of a differential equation with a neural network, PI-…