REVIEW 7 cited by
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However, existing restoration backbones often face the dilemma between global receptive fields and efficient computation, hindering their application in practice. Recently, the Selective Structured State Space Model, especially the improved version Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a way to resolve the above dilemma. However, the standard Mamba still faces certain challenges in low-level vision such as local pixel forgetting and channel redundancy. In this work, we introduce a simple but effective baseline, named MambaIR, which introduces both local enhancement and channel attention to improve the vanilla Mamba. In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy. Extensive experiments demonstrate the superiority of our method, for example, MambaIR outperforms SwinIR by up to 0.45dB on image SR, using similar computational cost but with a global receptive field. Code is available at \url{https://github.com/csguoh/MambaIR}.
Forward citations
Cited by 7 Pith papers
-
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
EAMamba introduces channel-grouped multi-head selective scanning whose cost does not grow with the number of scan directions, and reports 31-89% FLOPs reductions with comparable PSNR across denoising, super-resolution...
-
PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors
PBR-SR super-resolves PBR texture maps (albedo, roughness, metallic, normal) in a zero-shot way by optimizing textures so differentiable renderings match super-resolved multi-view renderings from a pretrained image SR model.
-
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
PMA adapts frozen point cloud models by ordering and fusing all intermediate layer features with Mamba, achieving parameter-efficient gains on ScanObjectNN, ModelNet40, and ShapeNetPart.
-
VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mamba
VEMamba applies Mamba state-space models with axial-lateral chunked scanning and MoCo-based degradation learning to achieve efficient isotropic reconstruction of volume electron microscopy data.
-
Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding
A Transformer-Mamba hybrid with multi-cross attention and multi-scan state-space fusion reports state-of-the-art PSNR and SSIM on synthetic burst super-resolution benchmarks.
-
Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining
The paper introduces a dual-branch state-space video deraining model with a dynamic stacking filter and semi-supervised median stacking loss, showing top PSNR across three benchmarks and new downstream task gains on a...
-
Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers
TCD-Net couples a ViT denoiser with "causal" regularizers (de-centering, orthogonality, Nano Banana Pro distillation) and reports marginal PSNR shifts of ≤0.08 dB on some benchmarks, with no error bars or code.
Discussion (0). Continue with ORCID to comment.