# Multi-Exposure Image Fusion via Distilled 3D LUT Grid with Editable Mode

arXiv: https://arxiv.org/abs/2412.13749 · HTML: https://mlsanity.com/paper/2412.13749/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset](https://mlsanity.com/paper/1908.00682/) (2019)
- [Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables](https://mlsanity.com/paper/2108.08697/) (2021)
- [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (2021)
- [SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement](https://mlsanity.com/paper/2207.08351/) (2022)
- [StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement](https://mlsanity.com/paper/2107.12898/) (2021)
- [TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning](https://mlsanity.com/paper/2112.01030/) (2021)
- [Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation](https://mlsanity.com/paper/2003.12473/) (2020)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Single Image Super-Resolution via a Dual Interactive Implicit Neural Network](https://mlsanity.com/paper/2210.12593/) (2022)
- [Progressive Feature Fusion Network for Realistic Image Dehazing](https://mlsanity.com/paper/1810.02283/) (2018)
- [Single UHD Image Dehazing via Interpretable Pyramid Network](https://mlsanity.com/paper/2202.08589/) (2022)
- [BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies](https://mlsanity.com/paper/2108.09376/) (2021)
- [Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network](https://mlsanity.com/paper/2204.09213/) (2022)

## Abstract (arXiv)

With the rising imaging resolution of handheld devices, existing multi-exposure image fusion algorithms struggle to generate a high dynamic range image with ultra-high resolution in real-time. Apart from that, there is a trend to design a manageable and editable algorithm as the different needs of real application scenarios. To tackle these issues, we introduce 3D LUT technology, which can enhance images with ultra-high-definition (UHD) resolution in real time on resource-constrained devices. However, since the fusion of information from multiple images with different exposure rates is uncertain, and this uncertainty significantly trials the generalization power of the 3D LUT grid. To address this issue and ensure a robust learning space for the model, we propose using a teacher-student network to model the uncertainty on the 3D LUT grid.Furthermore, we provide an editable mode for the multi-exposure image fusion algorithm by using the implicit representation function to match the requirements in different scenarios. Extensive experiments demonstrate that our proposed method is highly competitive in efficiency and accuracy.