# Taming Lookup Tables for Efficient Image Retouching

arXiv: https://arxiv.org/abs/2403.19238 · HTML: https://mlsanity.com/paper/2403.19238/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://mlsanity.com/paper/2003.13985/) (2020)
- [Conditional Sequential Modulation for Efficient Global Image Retouching](https://mlsanity.com/paper/2009.10390/) (2020)
- [Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables](https://mlsanity.com/paper/2108.08697/) (2021)
- [PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency](https://mlsanity.com/paper/2105.09180/) (2021)
- [Deep White-Balance Editing](https://mlsanity.com/paper/2004.01354/) (2020)
- [SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement](https://mlsanity.com/paper/2207.08351/) (2022)
- [4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement](https://mlsanity.com/paper/2209.01749/) (2022)
- [Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2207.12987/) (2022)
- [RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters](https://mlsanity.com/paper/2303.08682/) (2023)
- [Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution](https://mlsanity.com/paper/2312.06101/) (2023)

## Built on by (most cited first, 12 of 12)

- [DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables](https://mlsanity.com/paper/2503.15931/) (2025)
- [NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results](https://mlsanity.com/paper/2505.18988/) (2025)
- [Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables](https://mlsanity.com/paper/2508.16121/) (2025)
- [RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models](https://mlsanity.com/paper/2510.08054/) (2025)
- [High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network](https://mlsanity.com/paper/2510.11613/) (2025)
- [Learning Differential Pyramid Representation for Tone Mapping](https://mlsanity.com/paper/2412.01463/) (2024)
- [CameraMaster: Unified Camera Semantic-Parameter Control for Photography Retouching](https://mlsanity.com/paper/2511.21024/) (2025)
- [ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration](https://mlsanity.com/paper/2603.00906/) (2026)
- [Anisotropic Pooling for LUT-realizable CNN Image Restoration](https://mlsanity.com/paper/2510.21437/) (2025)
- [LoR-LUT: Learning Compact 3D Lookup Tables via Low-Rank Residuals](https://mlsanity.com/paper/2602.22607/) (2026)
- [GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation](https://mlsanity.com/paper/2605.19889/) (2026)
- [LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement](https://mlsanity.com/paper/2609.33593/) (2026)

## Abstract (arXiv)

The widespread use of high-definition screens in edge devices, such as end-user cameras, smartphones, and televisions, is spurring a significant demand for image enhancement. Existing enhancement models often optimize for high performance while falling short of reducing hardware inference time and power consumption, especially on edge devices with constrained computing and storage resources. To this end, we propose Image Color Enhancement Lookup Table (ICELUT) that adopts LUTs for extremely efficient edge inference, without any convolutional neural network (CNN). During training, we leverage pointwise (1x1) convolution to extract color information, alongside a split fully connected layer to incorporate global information. Both components are then seamlessly converted into LUTs for hardware-agnostic deployment. ICELUT achieves near-state-of-the-art performance and remarkably low power consumption. We observe that the pointwise network structure exhibits robust scalability, upkeeping the performance even with a heavily downsampled 32x32 input image. These enable ICELUT, the first-ever purely LUT-based image enhancer, to reach an unprecedented speed of 0.4ms on GPU and 7ms on CPU, at least one order faster than any CNN solution. Codes are available at https://github.com/Stephen0808/ICELUT.