UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion
Zixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You, Zheming Lu, Fan Zhang, Shi Guo, Tianfan Xue
Abstract
to potential alignment issue or lighting variations. Moreover, by utilizing the image prior of the generative model, our model also generates natural tone mapping, even for very high-dynamic range scenes. Our approach outperforms HDR-Transformer on latest HDR benchmarks. Moreover, to test its performance in ultra high dynamic range scenes, we capture a new real-world exposure fusion benchmark, UltraFusion dataset, with exposure differences up to 9 stops, and experiments show that UltraFusion can generate beautiful and high-quality fusion results under various scenarios. Code and data will be available at https: //openimaginglab.github.io/UltraFusion .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 528c75fb-43fd-41d5-9277-d5a6b2bc11b2Cited by top-tier papers11
- A Unified Solution to Video Fusion: From Multi-Frame Learning to BenchmarkingZixiang Zhao, Haowen Bai, Bingxin Ke, Yukun Cui et al.NeurIPS 2025 · 21 citations
- UltraLED: Learning to See Everything in Ultra-High Dynamic Range ScenesYuang Meng, Xin Jin, Lina Lei, Chun-Le Guo et al.NeurIPS 2025 · 8 citations
- DA-VAE: Plug-in Latent Compression for Diffusion via Detail AlignmentXin Cai, Zhiyuan You, Zhoutong Zhang, Tianfan XueCVPR 2026 · 3 citations
- S2R-HDR: A Large-Scale Rendered Dataset for HDR FusionYujin Wang, Jiarui Wu, Yichen Bian, Fan Zhang et al.ICLR 2026 · 3 citations
- F^2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion ModelingHuanjing Yue, Dawei Li, Shaoxiong Tu, Jingyu YangCVPR 2026
Builds on27
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsChenlin Meng, Yutong He, Yang Song, Jiaming Song et al.ICLR 2022 · 2,128 citations
- RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsAndreas Lugmayr, Martin Danelljan, Andrés Romero, Fisher Yu et al.CVPR 2022 · 1,425 citations
Related papers
- HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark DatasetGuanying Chen, Chaofeng Chen, Shi Guo, Zhetong Liang et al.ICCV 2021 · 70 citations
- Improving Dynamic HDR Imaging with Fusion TransformerRufeng Chen, Bolun Zheng, Hua Zhang, Quan Chen et al.AAAI 2023 · 34 citations
- Revisiting the Stack-Based Inverse Tone MappingNing Zhang, Yuyao Ye, Yang Zhao, Ronggang WangCVPR 2023
- Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image DatasetShuaizheng Liu, Xindong Zhang, Lingchen Sun, Zhetong Liang et al.CVPR 2023
- GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the WildChao Wang, Ana Serrano, Xingang Pan, Bin Chen et al.ICCV 2023 · 29 citations
