paper-with-me

홈 › Papers

Global Modeling Matters: A Fast, Lightweight and Effective Baseline for Efficient Image Restoration

2025-07-18 · Xingyu Jiang, Ning Gao, Hongkun Dou, Xiuhui Zhang, Xiaoqing Zhong, Yue Deng, Hongjue Li arxiv

Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution to this challenge and has been widely discussed in the literature. Although recent transformer-based approaches have made remarkable progress in image restoration, their increasing system complexity poses significant challenges for real-time processing, particularly in real-world deployment scenarios. To this end, most existing methods attempt to simplify the self-attention mechanism, such as by channel self-attention or state space model. However, these methods primarily focus on network architecture while neglecting the inherent characteristics of image restoration itself. In this context, we explore a pyramid Wavelet-Fourier iterative pipeline to demonstrate the potential of Wavelet-Fourier processing for image restoration. Inspired by the above findings, we propose a novel and efficient restoration baseline, named Pyramid Wavelet-Fourier Network (PW-FNet). Specifically, PW-FNet features two key design principles: 1) at the inter-block level, integrates a pyramid wavelet-based multi-input multi-output structure to achieve multi-scale and multi-frequency bands decomposition; and 2) at the intra-block level, incorporates Fourier transforms as an efficient alternative to self-attention mechanisms, effectively reducing computational complexity while preserving global modeling capability. Extensive experiments on tasks such as image deraining, raindrop removal, image super-resolution, motion deblurring, image dehazing, image desnowing and underwater/low-light enhancement demonstrate that PW-FNet not only surpasses state-of-the-art methods in restoration quality but also achieves superior efficiency, with significantly reduced parameter size, computational cost and inference time.

📄 PDF Abstract BibTeX arXiv:2507.13663

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionImage RestorationImage Dehazing

Similar Papers 제목 키워드 기반

Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning

2024-12-26 · Ran Ma, Yixiong Zou, Yuhua Li, Ruixuan Li

Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the large domain gap makes CDFSL a challenging…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot Learning

LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation

2025-06-05 · Biao Guo, Fangmin Guo, Guibo Luo, Xiaonan Luo 외

Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the global context required for detecting se…

Multi-Person Pose EstimationPose Estimation

Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation

2024-12-15 · Ling-An Zeng, Guohong Huang, Gaojie Wu, Wei-Shi Zheng

Despite the significant role text-to-motion (T2M) generation plays across various applications, current methods involve a large number of parameters and suffer from slow inference speeds, leading to high usage costs. To …

GPUMambaMotion Generation

Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition

2026-04-24 · Shunpeng Chen, Yukun Song, Changwei Wang, Rongtao Xu 외 arxiv

Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasing caused by irrelevant regions and ineff…

Visual Place Recognition

mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling

2025-07-02 · Tristan Torchet, Christian Metzner, Karthik Charan Raghunathan, Jimmy Weber 외 arxiv

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open chall…

Audio Classification