# ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration

arXiv: https://arxiv.org/abs/2603.00906 · HTML: https://mlsanity.com/paper/2603.00906/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [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)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions](https://mlsanity.com/paper/1711.08141/) (2017)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024)
- [Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2207.12987/) (2022)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [Taming Lookup Tables for Efficient Image Retouching](https://mlsanity.com/paper/2403.19238/) (2024)
- [Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution](https://mlsanity.com/paper/2312.06101/) (2023)
- [AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning](https://mlsanity.com/paper/2503.01565/) (2025)
- [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://mlsanity.com/paper/2303.04336/) (2023)

## Built on by (most cited first, 2 of 2)

- [LPM: Industrial-Scale Generative Video Restoration](https://mlsanity.com/paper/2607.13460/) (2026)
- [LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement](https://mlsanity.com/paper/2609.33593/) (2026)

## Abstract (arXiv)

Look-Up Table based methods have emerged as a promising direction for efficient image restoration tasks. Recent LUT-based methods focus on improving their performance by expanding the receptive field. However, they inevitably introduce extra computational and storage overhead, which hinders their deployment in edge devices. To address this issue, we propose ShiftLUT, a novel framework that attains the largest receptive field among all LUT-based methods while maintaining high efficiency. Our key insight lies in three complementary components. First, Learnable Spatial Shift module (LSS) is introduced to expand the receptive field by applying learnable, channel-wise spatial offsets on feature maps. Second, we propose an asymmetric dual-branch architecture that allocates more computation to the information-dense branch, substantially reducing inference latency without compromising restoration quality. Finally, we incorporate a feature-level LUT compression strategy called Error-bounded Adaptive Sampling (EAS) to minimize the storage overhead. Compared to the previous state-of-the-art method TinyLUT, ShiftLUT achieves a 3.8× larger receptive field and improves an average PSNR by over 0.21 dB across multiple standard benchmarks, while maintaining a small storage size and inference time. The code is available at: https://github.com/Sailor-t/ShiftLUT .