# ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion

arXiv: https://arxiv.org/abs/2607.03110 · HTML: https://mlsanity.com/paper/2607.03110/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Image Fusion via Vision-Language Model](https://mlsanity.com/paper/2402.02235/) (2024)
- [Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks](https://mlsanity.com/paper/2503.16930/) (2025)
- [Benchmarking and Comparing Multi-exposure Image Fusion Algorithms](https://mlsanity.com/paper/2007.15156/) (2020)
- [Towards High-quality HDR Deghosting with Conditional Diffusion Models](https://mlsanity.com/paper/2311.00932/) (2023)
- [Alignment-free HDR Deghosting with Semantics Consistent Transformer](https://mlsanity.com/paper/2305.18135/) (2023)
- [Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration](https://mlsanity.com/paper/2107.06211/) (2021)
- [SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging](https://mlsanity.com/paper/2407.16308/) (2024)
- [MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion](https://mlsanity.com/paper/2309.11847/) (2023)
- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm](https://mlsanity.com/paper/2506.23537/) (2025)
- [EMEF: Ensemble Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12734/) (2023)
- [OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems](https://mlsanity.com/paper/2412.11165/) (2024)
- [GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction](https://mlsanity.com/paper/2403.17837/) (2024)
- [Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion](https://mlsanity.com/paper/2503.07235/) (2025)
- [S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion](https://mlsanity.com/paper/2504.07667/) (2025)
- [Deep LoRA-Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2602.18697/) (2026)

## Abstract (arXiv)

Multi-Exposure Fusion (MEF) effectively extends dynamic range, but practical deployment is hindered by motion-induced ghosting and the scarcity of high-quality dynamic benchmarks. Current benchmarks largely neglect dynamic scenes and lack reliable ground truth, making it difficult to handle the complexity of real-world motions. In response, we introduce ExpoMotion, a large-scale benchmark designed to evaluate deghosting capabilities. Comprising 1,738 sequences and 10,909 images across diverse environments, it covers a wide range of motions and provides high-fidelity GTs constructed through an expert-guided acquisition pipeline. To tackle the complex dynamics and extreme conditions captured in this benchmark, we propose the Householder Orthogonal Projection network (HOP), which revisits MEF deghosting from a mathematical perspective via Householder transformation, decoupling multi-frame alignment into exposure pre-alignment and ghost filtering. Specifically, the Global Priors Illumination Alignment (GPIA) module first rectifies drastic dynamic range discrepancies by utilizing global statistics for exposure harmonization. Regarding ghost removal, our Householder Orthogonal Attention (HOA) models artifacts as orthogonal perturbations. By employing a dynamic Householder reflector, HOA effectively projects ghosts out of the feature manifold while preserving high-frequency details. Experiments demonstrate that our ExpoMotion dataset enables superior generalization and artifact-free detail restoration, while also validating the effectiveness and efficiency of the HOP method. The dataset and code are available at https://github.com/Leo-LiuYao/ExpoMotion.