Research map / Video / Video segmentation and tracking
HDR Video Reconstruction: A Coarse-To-Fine Network and a Real-World Benchmark Dataset
Guanying Chen, Chaofeng Chen, Shi Guo, Zhetong Liang, Kwan-Yee K. Wong, Lei Zhang
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 RefineNet after CoarseNet (ablation) | Coarse-to-fine HDR video network · Synthetic (2-Exp) | PSNR: 39.25 -> 40.34 | Improved |
| add RefineNet after CoarseNet (ablation) | Coarse-to-fine HDR video network · Real dynamic scenes with GT (2-Exp) | PSNR: 44.43 -> 45.46 | Improved |
| add RefineNet after CoarseNet (ablation) | Coarse-to-fine HDR video network · Real static scenes with GT (2-Exp) | PSNR: 40.62 -> 41.18 | Improved |
| add CoarseNet before RefineNet (ablation) | Coarse-to-fine HDR video network · Synthetic (2-Exp) | PSNR: 39.69 -> 40.34 | Improved |
| add CoarseNet before RefineNet (ablation) | Coarse-to-fine HDR video network · Real static scenes with GT (2-Exp) | PSNR: 37.61 -> 41.18 | Improved |
| add deformable alignment module (ablation) | Coarse-to-fine HDR video network · Synthetic (2-Exp) | PSNR: 39.72 -> 40.34 | Improved |
| add deformable alignment module (ablation) | Coarse-to-fine HDR video network · Real dynamic scenes with GT (2-Exp) | PSNR: 45.09 -> 45.46 | Improved |
| add temporal attention fusion instead of concatenation + conv (ablation) | Coarse-to-fine HDR video network · Synthetic (2-Exp) | PSNR: 40.03 -> 40.34 | Improved |
| add temporal attention fusion instead of concatenation + conv (ablation) | Coarse-to-fine HDR video network · Real static scenes with GT (2-Exp) | HDR-VDP-2: 76.12 -> 76.15 | No clear effect |
| add temporal attention fusion instead of concatenation + conv (ablation) | Coarse-to-fine HDR video network · Real dynamic scenes with GT (2-Exp) | PSNR: 45.17 -> 45.46 | Improved |
| coarse-to-fine network vs Kalantari19 | Coarse-to-fine HDR video network · Synthetic (2-Exp) | PSNR: 37.48 -> 40.34 | Improved |
| coarse-to-fine network vs Kalantari13 on 3-Exp static scenes | Coarse-to-fine HDR video network · Real static scenes with GT (3-Exp) | PSNR: 39.77 -> 39.75 | No clear effect |
Closest papers by meaning
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.94)
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · similarity 0.92)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.90)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.89)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.89)
- High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm (CVPR 2025 · similarity 0.88)
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.
