Research map / Video / Video segmentation and tracking
F^2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
Huanjing Yue, Dawei Li, Shaoxiong Tu, Jingyu 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 flow adapter (ablation) | F2HDR stage I · DeepHDRVideo | PSNR-T: 43.06 -> 43.39 | Improved |
| add flow adapter (ablation) | F2HDR stage I · Real-HDRV | PSNR-T: 40.29 -> 40.61 | Improved |
| add stage II refinement to stage I (ablation) | F2HDR · DeepHDRVideo | PSNR-T: 43.39 -> 43.87 | Improved |
| add physical motion mask (ablation) | F2HDR stage II · DeepHDRVideo | PSNR-T: 43.68 -> 43.87 | Improved |
| use physical motion modeling instead of CNN-learned mask (ablation) | F2HDR · Real-HDRV | PSNR-T: 40.93 -> 41.01 | Improved |
| add flow adapter (ablation) | F2HDR flow · Real-HDRV flow evaluation | optical flow EPE: 1.81 -> 2.08 | Hurt |
| add flow adapter (ablation) | F2HDR flow · Real-HDRV flow evaluation | LDR warping PSNR: 30.39 -> 30.84 | Improved |
| F2HDR vs NECHDR | F2HDR · DeepHDRVideo | PSNR-T: 43.44 -> 43.87 | Improved |
| F2HDR vs NECHDR | F2HDR · Real-HDRV | PSNR-L: 50.41 -> 50.51 (SSIM-L 0.9952 -> 0.9949) | Mixed |
| F2HDR vs HDRFlow inference | F2HDR · Inference time 1920x1080 | seconds: 0.076 -> 0.290 | Hurt |
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.
- HDRFlow — HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024) · better on 7 of 8 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
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · similarity 0.92)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.91)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.89)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.87)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.87)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.87)
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.
