Research map / Architectures and efficiency / RNNs and normalization
Learning a Practical SDR-to-HDRTV Up-Conversion Using New Dataset and Degradation Models
Cheng Guo, Leidong Fan, Ziyu Xue, Xiuhua Jiang
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 |
|---|---|---|---|
| Use HDRTV4K labels instead of Zeng20 labels (ablation) | LSN trained with the proposed degradation models · 12 4K SDR test videos | FWGP: 0.0593 -> 0.6873 | Improved |
| Use HDRTV4K labels instead of Zeng20 labels (ablation) | LSN trained with the proposed degradation models · 12 4K SDR test videos | EHL: 0.345 -> 2.599 | Improved |
| Use HDRTV4K labels instead of HDRTV1K labels (ablation) | LSN trained with the proposed degradation models · 12 4K SDR test videos | FWGP: 1.7494 -> 0.6873 | Hurt |
| Use the proposed degradation models instead of YouTube DM (ablation) | LSN trained on HDRTV4K · 12 4K SDR test videos | FHLP: 0.2168 -> 4.2509 | Improved |
| Use the proposed degradation models instead of YouTube DM (ablation) | LSN trained on HDRTV4K · 12 4K SDR test videos | ASL: 5.874 -> 7.522 | Improved |
| Use the proposed degradation models instead of Reinhard DM (ablation) | LSN trained on HDRTV4K · 12 4K SDR test videos | FWGP: 0.0000 -> 0.6873 | Improved |
| Use the proposed degradation models instead of Reinhard DM (ablation) | LSN trained on HDRTV4K · 12 4K SDR test videos | EHL: 0.734 -> 2.599 | Improved |
| Replace HDRTV4K labels with HDRTV1K labels (ablation) | LSN trained with the proposed degradation models · 12 4K SDR test videos | FHLP: 2.9405 -> 4.2509 | Hurt |
Closest papers by meaning
- A New Journey From SDRTV to HDRTV (ICCV 2021 · similarity 0.90)
- HDRMovieformer: A Transformer Framework and Benchmark for Cinematic SDR-to-HDR Conversion (AAAI 2026 · similarity 0.89)
- RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning (AAAI 2026 · similarity 0.87)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.85)
- High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm (CVPR 2025 · similarity 0.84)
- Perceptual Assessment and Optimization of HDR Image Rendering (CVPR 2024 · similarity 0.83)
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.
