Research map / Video / Video generation
A New Journey From SDRTV to HDRTV
Xiangyu Chen, Zhengwen Zhang, Jimmy S. Ren, Lynhoo Tian, Yu Qiao, Chao Dong
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 color condition network to the base network (ablation) | AGCM · HDRTV1K test | PSNR: 36.14 -> 36.88 | Improved |
| add color condition network to the base network (ablation) | AGCM · HDRTV1K test | DeltaE_ITP: 10.43 -> 9.78 | Improved |
| add local enhancement after AGCM (ablation) | HDRTVNet · HDRTV1K test | PSNR: 36.88 -> 37.61 | Improved |
| add local enhancement after AGCM (ablation) | HDRTVNet · HDRTV1K test | HDR-VDP3: 8.464 -> 8.613 | Improved |
| add highlight generation GAN after LE (ablation) | HDRTVNet · HDRTV1K test | PSNR: 37.61 -> 37.21 | Hurt |
| add highlight generation GAN after LE (ablation) | HDRTVNet · HDRTV1K test | DeltaE_ITP: 8.89 -> 9.11 | Hurt |
| add highlight generation GAN after LE (ablation) | HDRTVNet · HDRTV1K test | SR-SIM: 0.9967 -> 0.9968 | No clear effect |
| apply local enhancement first instead of after AGCM (ablation) | HDRTVNet · HDRTV1K test | visual artifacts | Hurt |
| remove pixel shuffle layer instead of downsampling in joint SR methods (ablation) | Deep SR-ITM / JSI-GAN · HDRTV1K test | PSNR | No clear effect |
| shuffle pixels of the condition network input (ablation) | AGCM condition network · HDRTV1K test | PSNR | No clear effect |
| AGCM versus Ada-3DLUT at fewer parameters | AGCM · HDRTV1K test | PSNR: 36.88 vs 36.22 | Mixed |
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.
- Deep SR-ITM — Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications (ICCV 2019) · better on 2 of 2 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
- Learning a Practical SDR-to-HDRTV Up-Conversion Using New Dataset and Degradation Models (CVPR 2023 · similarity 0.90)
- Perceptual Assessment and Optimization of HDR Image Rendering (CVPR 2024 · similarity 0.83)
- Color Event Enhanced Single-Exposure HDR Imaging (AAAI 2024 · similarity 0.82)
- HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (NeurIPS 2024 · similarity 0.81)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.81)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.81)
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.
