paper-with-me

Papers

FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss

2024-08-25 · Meiyi Wei, Liu Xie, Ying Sun, Gang Chen

Recent advancements in local Implicit Neural Representation (INR) demonstrate its exceptional capability in handling images at various resolutions. However, frequency discrepancies between high-resolution (HR) and ground-truth images, especially at larger scales, result in significant artifacts and blurring in HR images. This paper introduces Frequency Consistency for Implicit Neural Representation (FreqINR), an innovative Arbitrary-scale Super-resolution method aimed at enhancing detailed textures by ensuring spectral consistency throughout both training and inference. During training, we employ Adaptive Discrete Cosine Transform Frequency Loss (ADFL) to minimize the frequency gap between HR and ground-truth images, utilizing 2-Dimensional DCT bases and focusing dynamically on challenging frequencies. During inference, we extend the receptive field to preserve spectral coherence between low-resolution (LR) and ground-truth images, which is crucial for the model to generate high-frequency details from LR counterparts. Experimental results show that FreqINR, as a lightweight approach, achieves state-of-the-art performance compared to existing Arbitrary-scale Super-resolution methods and offers notable improvements in computational efficiency. The code for our method will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2408.13716

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencySuper-Resolution

Methods 이 논문이 사용한 방법론

Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising

2026-04-18 · Ligen Shi, Zengyu Pang, Chang Liu, Shuchen Sun 외 arxiv

Addressing the issues of severe noise and high frequency structural degradation in visible images under low-light conditions, this paper proposes a Near Infrared (NIR) aided low light image restoration method based on Fr…

Image RestorationImage Denoising

Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing

2026-06-15 · Yuhan Chen, Ying Fang, Guofa Li, Wenxuan Yu 외 arxiv

Single image dehazing continues to be hindered by the loss of high-frequency details and the difficulty of accurate physical scattering modeling. To address these issues, we propose Fi-Gaussian, a frequency-aware implici…

Single Image DehazingPoint Clouds

Frequency Decoupled Framework for Screen Content Image Super-Resolution

2026-06-08 · Xufei Wang, Qicheng Zhang, Qi Wu, Ziyang Gu 외 arxiv

Methods based on implicit neural representations have demonstrated superior performance in Screen Content Image Super-Resolution (SCISR) . However, they overlooked the inherent frequency characteristics, leading to subop…

Image Super-Resolution

FLAIR: Frequency- and Locality-Aware Implicit Neural Representations

2025-08-19 · Sukhun Ko, Seokhyun Youn, Dahyeon Kye, Kyle Min 외 arxiv

Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driven significant advances in various visio…

3D Shape ReconstructionNovel View Synthesis

Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations

2026-04-03 · Ligen Shi, Jun Qiu, Yuhang Zheng, Zengyu Pang 외 arxiv

Fourier-encoded implicit neural representations (INRs) have shown strong capability in modeling continuous signals from discrete samples. However, conventional Fourier feature mappings use a fixed set of frequencies over…