Research map / Architectures and efficiency / Attention and transformers
HDRMovieformer: A Transformer Framework and Benchmark for Cinematic SDR-to-HDR Conversion
Xianwei Li, Huiyuan Fu, Chuanming Wang, Huadong Ma
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 Luminance Estimator (ablation) | HDRMovieformer · HDRMovie7K test | PSNR: 53.70 -> 55.15 | Improved |
| add LG-MSA instead of standard global MSA (ablation) | HDRMovieformer · HDRMovie7K test | PSNR: 54.45 -> 55.15 | Improved |
| add LG-MSA instead of standard global MSA (ablation) | HDRMovieformer · HDRMovie7K test | SSIM: 0.9952 -> 0.9941 | Hurt |
| add Chroma Refiner instead of conv head (ablation) | HDRMovieformer · HDRMovie7K test | ΔEITP: 1.494 -> 1.461 | Improved |
| add Chroma Refiner instead of conv head (ablation) | HDRMovieformer · HDRMovie7K test | SSIM: 0.9936 -> 0.9941 | Hurt |
| add WCG Loss to RGB L1 loss (ablation) | HDRMovieformer · HDRMovie7K test | ΔEITP: 1.511 -> 1.461 | Improved |
| add WCG Loss to RGB L1 loss (ablation) | HDRMovieformer · HDRMovie7K test | SSIM: 0.9962 -> 0.9941 | Hurt |
| use HDRMovieformer instead of UHDformer | HDRMovie7K baseline · HDRMovie7K test | PSNR(Y) (PU space): 55.8492 -> 57.3160 | Improved |
| use HDRMovieformer instead of ICTCPNet | HDRMovie1K baseline · HDRMovie1K test | PSNR(Y) (PU space): 41.4888 -> 43.7938 | Improved |
| use HDRMovieformer instead of OKNet | HDRMovie1K baseline · HDRMovie1K test | HDR-VDP3: 8.7956 -> 8.7830 | No clear effect |
| use HDRMovieformer instead of HDRTVNet in subjective test | HDRMovie clips · Subjective ACR (20 participants), contrast and shadow detail | mean rating | Hurt |
Closest papers by meaning
- DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models (ECCV 2026 · similarity 0.90)
- Learning a Practical SDR-to-HDRTV Up-Conversion Using New Dataset and Degradation Models (CVPR 2023 · similarity 0.89)
- Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos (CVPR 2026 · similarity 0.88)
- Perceptual Assessment and Optimization of HDR Image Rendering (CVPR 2024 · similarity 0.87)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.86)
- LEDiff: Latent Exposure Diffusion for HDR Generation (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.
