Tehnički vjesnik, Vol. 33 No. 1, 2026.
Izvorni znanstveni članak
https://doi.org/10.17559/TV-20250204002330
HFDDLap: High-Low Frequency Differentiation Dynamic Laplacian Pyramid Network for Image Super-Resolution
Peituan Liu
; Tiangong University, School of Computer Science and Technology, Tianjin 300387, China
Tie Li
; Tiangong University, School of Computer Science and Technology, Tianjin 300387, China
*
Rui Li
; Tiangong University, School of Computer Science and Technology, Tianjin 300387, China
Bo Song
; Tiangong University, School of Computer Science and Technology, Tianjin 300387, China
* Dopisni autor.
Sažetak
Existing single image super-resolution (SR) algorithms based on convolution neural networks (CNNs) have achieved usable visual results. However, they often encounter artifacts and blurring, particularly at large scaling factors (e.g., 4×, 8×), due to significant loss of high-frequency information. To address these challenges, we propose a novel high-low frequency differentiation dynamic Laplacian pyramid network (HFDDLap). Our approach introduces a learnable high-low frequency differentiation convolution (HLC) within high-low frequency differentiation residual channel attention blocks (HL-RCAB) to effectively capture and differentiate high- and low-frequency components, enhancing detail preservation. Additionally, we employ a dynamic deconvolution (DDC) that adaptively generates upsampling kernels based on input features, improving reconstruction accuracy by reducing feature distortion. Extensive experiments on 4× and 8× SR demonstrate that our proposed method effectively reconstructs edge details, produces satisfactory SR results and outperforms some state-of-the-art (SOTA) methods in terms of evaluation metrics.
Ključne riječi
dynamic deconvolution; Laplacian pyramid network; nonlinear mapping; single image super-resolution
Hrčak ID:
342661
URI
Datum izdavanja:
31.12.2025.
Posjeta: 493 *