WaMaIR: Image Restoration via Multiscale Wavelet Convolutions and Mamba-based Channel Modeling with Texture Enhancement
This work addresses texture detail restoration in image restoration for computer vision applications, representing an incremental improvement over existing CNN-based methods.
The paper tackles the problem of restoring fine texture details in image restoration by proposing WaMaIR, a framework that uses multiscale wavelet convolutions and Mamba-based channel modeling with texture enhancement, achieving state-of-the-art performance in image restoration with efficient computational results.
Image restoration is a fundamental and challenging task in computer vision, where CNN-based frameworks demonstrate significant computational efficiency. However, previous CNN-based methods often face challenges in adequately restoring fine texture details, which are limited by the small receptive field of CNN structures and the lack of channel feature modeling. In this paper, we propose WaMaIR, which is a novel framework with a large receptive field for image perception and improves the reconstruction of texture details in restored images. Specifically, we introduce the Global Multiscale Wavelet Transform Convolutions (GMWTConvs) for expandding the receptive field to extract image features, preserving and enriching texture features in model inputs. Meanwhile, we propose the Mamba-Based Channel-Aware Module (MCAM), explicitly designed to capture long-range dependencies within feature channels, which enhancing the model sensitivity to color, edges, and texture information. Additionally, we propose Multiscale Texture Enhancement Loss (MTELoss) for image restoration to guide the model in preserving detailed texture structures effectively. Extensive experiments confirm that WaMaIR outperforms state-of-the-art methods, achieving better image restoration and efficient computational performance of the model.