Research map / Video / Video segmentation and tracking
LRHDR: Learning Representation-enhanced HDR Video Reconstruction
Chenzhuo Liao, Xin Chen, Bingchen Li, Yu Meng, Tao Yue, Xuemei Hu
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 EIC encoder (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 44.51 -> 44.86 | Improved |
| add EIC encoder (ablation) | LRHDR · Cinematic Video (2-exposure) | PSNR_T: 40.01 -> 40.27 | Improved |
| add Representation Mapper to Base (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 44.51 -> 45.11 | Improved |
| add ACCR loss to RM (ablation) | LRHDR · Cinematic Video (2-exposure) | PSNR_T: 40.47 -> 40.61 | Improved |
| add ACCR loss to RM (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 45.11 -> 45.46 | Improved |
| add Vote Loss (ablation) | LRHDR · Cinematic Video (2-exposure) | PSNR_T: 40.97 -> 41.11 | Improved |
| add Vote Loss (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | SSIM_T: 0.9733 -> 0.9753 | Improved |
| add Vote Loss (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 45.52 -> 45.89 | Improved |
| replace dense fusion network with APSWF sparse fusion (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 45.61 -> 45.89 | Improved |
| replace dense fusion network with APSWF sparse fusion (ablation) | LRHDR · Cinematic Video (2-exposure) | PSNR_T: 40.90 -> 41.11 | Improved |
| use ACCR with the prior fusion net instead of explicit alignment (HDRFlow) (ablation) | LRHDR · DeepHDRVideo dynamic scenes (2-exposure) | PSNR_T: 45.50 -> 45.61 | Improved |
| LRHDR vs NECHDR on HDR-VDP-2 | LRHDR · DeepHDRVideo (3-exposure) | HDR-VDP-2: 76.98 (NECHDR) vs 76.01 (LRHDR) | 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 4 of 4 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
- HDR Video Reconstruction: A Coarse-To-Fine Network and a Real-World Benchmark Dataset (ICCV 2021 · similarity 0.92)
- DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure Sequences (ICLR 2026 · similarity 0.92)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.91)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.90)
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · similarity 0.89)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · 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.
