Research map / Image generation / Image restoration
ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion
Yao Liu, Lishen Qu, Jie Liang, shihao zhou, Hui Zeng, Yabin Peng, Huipeng Lin, Lei Zhang, Jufeng Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add GPIA (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 27.8562 | Improved |
| add HOPU (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 27.9003 | Improved |
| replace GDFN with GGFN (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 27.8332 | Improved |
| add HOPU and GGFN together (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 28.2321 | Improved |
| add GPIA and GGFN together (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 28.1334 | Improved |
| add all three modules GPIA, HOPU, GGFN (ablation) | HOP-S baseline · Kalantari17 | PSNR (dB): 27.4526 -> 28.5011 | Improved |
| add all three modules (parameter cost) (ablation) | HOP-S baseline · Kalantari17 | Params (M): 3.3818 -> 3.6990 | Hurt |
| scale HOP-S to HOP-B | HOP · Kalantari17 | PSNR (dB): 28.501 -> 28.804 | Improved |
| use HOP-B instead of Restormer | Restormer · Kalantari17 | Params (M): 26.10 -> 15.69 | Improved |
| train on ExpoMotion instead of Kalantari17 | HOP-B · Sen+Tursen | MUSIQ: 57.87 -> 62.74 | Improved |
| train on ExpoMotion instead of RealHDRV | HOP-B · Sen+Tursen | MUSIQ: 60.89 -> 62.74 | Improved |
| use HOP-B instead of Restormer (same ExpoMotion training data) | Restormer · Sen+Tursen | MUSIQ: 62.32 -> 62.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 11 of 11 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range (ICML 2026 · similarity 0.89)
- There and Back Again: A Flexible-Frame Transformer for Multi-Exposure Fusion (ECCV 2026 · similarity 0.88)
- MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting (CVPR 2026 · similarity 0.87)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.85)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
