Related papers: MambaIRv2: Attentive State Space Restoration

MambaIRv2: Attentive State Space Restoration

URL: http://arxiv.org/abs/2411.15269v1
Date: Fri, 22 Nov 2024 12:45:12 GMT
Title: MambaIRv2: Attentive State Space Restoration
Authors: Hang Guo, Yong Guo, Yaohua Zha, Yulun Zhang, Wenbo Li, Tao Dai, Shu-Tao Xia, Yawei Li,
Abstract summary: We propose MambaIRv2, which equips Mamba with the non-causal modeling ability similar to ViTs to reach the attentive state space restoration model. Specifically, the proposed attentive state-space equation allows to attend beyond the scanned sequence and facilitate image unfolding with just one single scan.
Score: 96.4452232356586
License:
Abstract: The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends solely on its predecessors in the scanned sequence, restricts the full utilization of pixels across the image and thus presents new challenges in image restoration. In this work, we propose MambaIRv2, which equips Mamba with the non-causal modeling ability similar to ViTs to reach the attentive state space restoration model. Specifically, the proposed attentive state-space equation allows to attend beyond the scanned sequence and facilitate image unfolding with just one single scan. Moreover, we further introduce a semantic-guided neighboring mechanism to encourage interaction between distant but similar pixels. Extensive experiments show our MambaIRv2 outperforms SRFormer by \textbf{even 0.35dB} PSNR for lightweight SR even with \textbf{9.3\% less} parameters and suppresses HAT on classic SR by \textbf{up to 0.29dB}. Code is available at \url{https://github.com/csguoh/MambaIR}.

Related papers

Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution [42.259283231048954]
State Space Models (SSM) have shown strong representation ability in modeling long-range dependency with linear complexity. We propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR)
arXiv Detail & Related papers (2024-10-14T04:15:04Z)
MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs [14.42424591513825]
MambaCSR is a framework based on Mamba for the challenging compressed image super-resolution (CSR) task. We propose an efficient dual-interleaved scanning paradigm (DIS) for CSR, which is composed of two scanning strategies. Results on multiple benchmarks have shown the great performance of our MambaCSR in the compressed image super-resolution task.
arXiv Detail & Related papers (2024-08-21T16:30:45Z)
Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution [49.902047563260496]
We develop the first attempt to integrate the Vision State Space Model (Mamba) for remote sensing image (RSI) super-resolution. To achieve better SR reconstruction, building upon Mamba, we devise a Frequency-assisted Mamba framework, dubbed FMSR. Our FMSR features a multi-level fusion architecture equipped with the Frequency Selection Module (FSM), Vision State Space Module (VSSM), and Hybrid Gate Module (HGM)
arXiv Detail & Related papers (2024-05-08T11:09:24Z)
RSMamba: Remote Sensing Image Classification with State Space Model [25.32283897448209]
We introduce RSMamba, a novel architecture for remote sensing image classification. RSMamba is based on the State Space Model (SSM) and incorporates an efficient, hardware-aware design known as the Mamba. We propose a dynamic multi-path activation mechanism to augment Mamba's capacity to model non-temporal image data.
arXiv Detail & Related papers (2024-03-28T17:59:49Z)
Activating Wider Areas in Image Super-Resolution [23.52183937294807]
Vision Mamba (Vim) is capable of finding the most relevant and representative input pixels to reconstruct the corresponding high-resolution images. MMA achieves competitive or even superior performance compared to state-of-the-art SISR methods.
arXiv Detail & Related papers (2024-03-13T08:29:58Z)
MambaIR: A Simple Baseline for Image Restoration with State-Space Model [46.827053426281715]
We introduce MambaIR, which introduces both local enhancement and channel attention to improve the vanilla Mamba. Our method outperforms SwinIR by up to 0.45dB on image SR, using similar computational cost but with a global receptive field.
arXiv Detail & Related papers (2024-02-23T23:15:54Z)
Towards Lightweight Super-Resolution with Dual Regression Learning [58.98801753555746]
Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks. The SR problem is typically an ill-posed problem and existing methods would come with several limitations. We propose a dual regression learning scheme to reduce the space of possible SR mappings.
arXiv Detail & Related papers (2022-07-16T12:46:10Z)
UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution [74.82282301089994]
In this work, we propose UltraSR, a simple yet effective new network design based on implicit image functions. We show that spatial encoding is indeed a missing key towards the next-stage high-accuracy implicit image function. Our UltraSR sets new state-of-the-art performance on the DIV2K benchmark under all super-resolution scales.
arXiv Detail & Related papers (2021-03-23T17:36:42Z)
DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution [69.2432352477966]
Real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair.
arXiv Detail & Related papers (2020-02-25T18:24:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.