XYScanNet: An Interpretable State Space Model for Perceptual Image Deblurring
- URL: http://arxiv.org/abs/2412.10338v2
- Date: Sat, 01 Feb 2025 02:31:31 GMT
- Title: XYScanNet: An Interpretable State Space Model for Perceptual Image Deblurring
- Authors: Hanzhou Liu, Chengkai Liu, Jiacong Xu, Peng Jiang, Mi Lu,
- Abstract summary: Deep state-space models (SSMs) are emerging as a promising alternative to CNN and Transformer networks.
We propose a novel slice-and-scan strategy that alternates scanning along intra-blur and inter-slices.
We develop XYScanNet, an SSM architecture integrated with a lightweight feature fusion module for enhanced image deblurring.
- Score: 6.9752432140704705
- License:
- Abstract: Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing Mamba-based restoration methods process the visual data by leveraging a flatten-and-scan strategy that converts image patches into a 1D sequence before scanning. However, this scanning paradigm ignores local pixel dependencies and introduces spatial misalignment by positioning distant pixels incorrectly adjacent, which reduces local noise-awareness and degrades image sharpness in low-level vision tasks. To overcome these issues, we propose a novel slice-and-scan strategy that alternates scanning along intra- and inter-slices. We further design a new Vision State Space Module (VSSM) for image deblurring, and tackle the inefficiency challenges of the current Mamba-based vision module. Building upon this, we develop XYScanNet, an SSM architecture integrated with a lightweight feature fusion module for enhanced image deblurring. XYScanNet, maintains competitive distortion metrics and significantly improves perceptual performance. Experimental results show that XYScanNet enhances KID by $17\%$ compared to the nearest competitor. Our code will be released soon.
Related papers
- DAMamba: Vision State Space Model with Dynamic Adaptive Scan [51.81060691414399]
State space models (SSMs) have recently garnered significant attention in computer vision.
We propose Dynamic Adaptive Scan (DAS), a data-driven method that adaptively allocates scanning orders and regions.
Based on DAS, we propose the vision backbone DAMamba, which significantly outperforms current state-of-the-art vision Mamba models in vision tasks.
arXiv Detail & Related papers (2025-02-18T08:12:47Z) - Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks [47.49096400786856]
State-Space Models (SSMs) have recently emerged as a powerful and efficient alternative to the long-standing transformer architecture.
We re-deriving modern selective state-space techniques, starting from a multidimensional formulation.
Mamba2D shows comparable performance to prior adaptations of SSMs for vision tasks, on standard image classification evaluations with the ImageNet-1K dataset.
arXiv Detail & Related papers (2024-12-20T18:50:36Z) - SEM-Net: Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSM [11.447968918063335]
Image inpainting aims to repair a partially damaged image based on the information from known regions of the images.
SEM-Net is a novel visual State Space model (SSM) vision network, modelling corrupted images at the pixel level while capturing long-range dependencies (LRDs) in state space.
arXiv Detail & Related papers (2024-11-10T00:35:14Z) - Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion [46.82975707531064]
Selective state space models (SSMs) excel at capturing long-range dependencies in 1D sequential data.
We propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space.
We show that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation.
arXiv Detail & Related papers (2024-10-19T12:56:58Z) - 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) - MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mamba [0.43512163406552]
State Space Models (SSMs) with Mamba have shown great promise for long-range dependency modeling with linear complexity.
To effectively organize and construct visual features within the 2D image space through 1D selective scan, we propose a novel Multi-Head Scan (MHS) module.
The resulting sub-embeddings, obtained from the multi-head scan process, are then integrated and ultimately projected back into the high-dimensional space.
arXiv Detail & Related papers (2024-06-10T03:24:43Z) - Efficient Visual State Space Model for Image Deblurring [83.57239834238035]
Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration.
We propose a simple yet effective visual state space model (EVSSM) for image deblurring.
arXiv Detail & Related papers (2024-05-23T09:13:36Z) - LocalMamba: Visual State Space Model with Windowed Selective Scan [45.00004931200446]
Key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling.
We introduce a novel local scanning strategy that divides images into distinct windows, effectively capturing local dependencies.
Our model significantly outperforms Vim-Ti by 3.1% on ImageNet with the same 1.5G FLOPs.
arXiv Detail & Related papers (2024-03-14T12:32:40Z) - VMamba: Visual State Space Model [98.0517369083152]
We adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity.
At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module.
arXiv Detail & Related papers (2024-01-18T17:55:39Z) - Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object
Structure via HyperNetworks [53.67497327319569]
We introduce a novel neural rendering technique to solve image-to-3D from a single view.
Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks.
Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
arXiv Detail & Related papers (2023-12-24T08:42:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.