# Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables arXiv: https://arxiv.org/abs/2303.14506 · HTML: https://mlsanity.com/paper/2303.14506/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 39 of its 104 references that are in the map. - First posted on arXiv 25 Mar 2023. ## Builds on (most cited first, 30 of 39) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019) - [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016) - [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (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) - [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018) - [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016) - [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015) - [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021) - [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018) - [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017) - [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017) - [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017) - [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016) - [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017) - [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021) - [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015) - [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018) - [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015) - [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018) - [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020) - [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) - [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](https://mlsanity.com/paper/1803.09454/) (2018) - [AdderNet: Do We Really Need Multiplications in Deep Learning?](https://mlsanity.com/paper/1912.13200/) (2019) - [Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables](https://mlsanity.com/paper/2108.08697/) (2021) - [DHP: Differentiable Meta Pruning via HyperNetworks](https://mlsanity.com/paper/2003.13683/) (2020) ## Built on by (most cited first, 11 of 11) - [DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables](https://mlsanity.com/paper/2503.15931/) (2025) - [In-Loop Filtering via Trained Look-Up Tables](https://mlsanity.com/paper/2407.10926/) (2024) - [IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution](https://mlsanity.com/paper/2507.09923/) (2025) - [Learning Differential Pyramid Representation for Tone Mapping](https://mlsanity.com/paper/2412.01463/) (2024) - [All-in-One Image Compression and Restoration](https://mlsanity.com/paper/2502.03649/) (2025) - [CameraMaster: Unified Camera Semantic-Parameter Control for Photography Retouching](https://mlsanity.com/paper/2511.21024/) (2025) - [LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation](https://mlsanity.com/paper/2407.09935/) (2024) - [In-Loop Filtering Using Learned Look-Up Tables for Video Coding](https://mlsanity.com/paper/2509.09494/) (2025) - [Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks](https://mlsanity.com/paper/2510.10522/) (2025) - [LogicIR: Logic Gate Networks for Image Restoration](https://mlsanity.com/paper/2606.26609/) (2026) - [Anisotropic Pooling for LUT-realizable CNN Image Restoration](https://mlsanity.com/paper/2510.21437/) (2025) ## Abstract (arXiv) The widespread usage of high-definition screens on edge devices stimulates a strong demand for efficient image restoration algorithms. The way of caching deep learning models in a look-up table (LUT) is recently introduced to respond to this demand. However, the size of a single LUT grows exponentially with the increase of its indexing capacity, which restricts its receptive field and thus the performance. To overcome this intrinsic limitation of the single-LUT solution, we propose a universal method to construct multiple LUTs like a neural network, termed MuLUT. Firstly, we devise novel complementary indexing patterns, as well as a general implementation for arbitrary patterns, to construct multiple LUTs in parallel. Secondly, we propose a re-indexing mechanism to enable hierarchical indexing between cascaded LUTs. Finally, we introduce channel indexing to allow cross-channel interaction, enabling LUTs to process color channels jointly. In these principled ways, the total size of MuLUT is linear to its indexing capacity, yielding a practical solution to obtain superior performance with the enlarged receptive field. We examine the advantage of MuLUT on various image restoration tasks, including super-resolution, demosaicing, denoising, and deblocking. MuLUT achieves a significant improvement over the single-LUT solution, e.g., up to 1.1dB PSNR for super-resolution and up to 2.8dB PSNR for grayscale denoising, while preserving its efficiency, which is 100× less in energy cost compared with lightweight deep neural networks. Our code and trained models are publicly available at https://github.com/ddlee-cn/MuLUT.