# KBNet: Kernel Basis Network for Image Restoration

arXiv: https://arxiv.org/abs/2303.02881 · HTML: https://mlsanity.com/paper/2303.02881/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 85 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 30 of 51)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)

## Built on by (most cited first, 30 of 33)

- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://mlsanity.com/paper/2401.15977/) (2024)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [TrustMark: Universal Watermarking for Arbitrary Resolution Images](https://mlsanity.com/paper/2311.18297/) (2023)
- [StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration](https://mlsanity.com/paper/2411.04925/) (2024)
- [ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection](https://mlsanity.com/paper/2310.13545/) (2023)
- [A Unified Conditional Framework for Diffusion-based Image Restoration](https://mlsanity.com/paper/2305.20049/) (2023)
- [DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables](https://mlsanity.com/paper/2503.15931/) (2025)
- [Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset](https://mlsanity.com/paper/2311.17396/) (2023)
- [Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather Conditions](https://mlsanity.com/paper/2409.01500/) (2024)
- [Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoising](https://mlsanity.com/paper/2502.06432/) (2025)
- [Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark](https://mlsanity.com/paper/2504.09555/) (2025)
- [Delving Deep into Engagement Prediction of Short Videos](https://mlsanity.com/paper/2410.00289/) (2024)
- [Learning to Translate Noise for Robust Image Denoising](https://mlsanity.com/paper/2412.04727/) (2024)
- [RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report](https://mlsanity.com/paper/2506.01947/) (2025)
- [Efficient Image Deblurring Networks based on Diffusion Models](https://mlsanity.com/paper/2401.05907/) (2024)
- [What is Wrong with End-to-End Learning for Phase Retrieval?](https://mlsanity.com/paper/2403.15448/) (2024)
- [OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions](https://mlsanity.com/paper/2504.13524/) (2025)
- [Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing](https://mlsanity.com/paper/2504.13975/) (2025)
- [LIR: A Lightweight Baseline for Image Restoration](https://mlsanity.com/paper/2402.01368/) (2024)
- [IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer](https://mlsanity.com/paper/2402.15784/) (2024)
- [Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration](https://mlsanity.com/paper/2412.12550/) (2024)
- [Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset](https://mlsanity.com/paper/2502.10452/) (2025)
- [An Ensemble Model for Distorted Images in Real Scenarios](https://mlsanity.com/paper/2309.14998/) (2023)
- [Passive Non-Line-of-Sight Imaging with Light Transport Modulation](https://mlsanity.com/paper/2312.16014/) (2023)
- [Amalgam: A Framework for Obfuscated Neural Network Training on the Cloud](https://mlsanity.com/paper/2406.03405/) (2024)
- [Video Denoising in Fluorescence Guided Surgery](https://mlsanity.com/paper/2411.09798/) (2024)
- [Adaptive High-Pass Kernel Prediction for Efficient Video Deblurring](https://mlsanity.com/paper/2412.01559/) (2024)
- [UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections](https://mlsanity.com/paper/2412.18276/) (2024)
- [SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAW](https://mlsanity.com/paper/2504.02345/) (2025)
- [Physics-Informed Graph Neural Networks for Frequency-Aware Optical Aberration Correction](https://mlsanity.com/paper/2512.05683/) (2025)

## Abstract (arXiv)

How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information adaptively. Recent transformer-based architectures achieve adaptive spatial aggregation. But they lack desirable inductive biases of convolutions and require heavy computational costs. In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggregation. Different kernel bases are trained to model different local structures. At each spatial location, they are linearly and adaptively fused by predicted pixel-wise coefficients to obtain aggregation weights. Based on the KBA module, we further design a multi-axis feature fusion (MFF) block to encode and fuse channel-wise, spatial-invariant, and pixel-adaptive features for image restoration. Our model, named kernel basis network (KBNet), achieves state-of-the-art performances on more than ten benchmarks over image denoising, deraining, and deblurring tasks while requiring less computational cost than previous SOTA methods.