Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking
Wei Jiang, Jiahao Cui, Yizheng Wu, Zhan Peng, Zhiyu Pan, Zhiguo Cao
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 vanilla mean teacher without rectifying pseudo labels (ablation) | GFHDR · Kalantari 6.7% GTs | PSNR-mu: 42.7220 -> 42.6509 | No clear effect |
| add uncertainty loss producing uncertainty scores (ablation) | BL+MT · Kalantari 6.7% GTs | PSNR-mu: 42.6509 -> 42.8893 | No clear effect |
| add patch-level masking (ablation) | BL+MT+L^k · Kalantari 6.7% GTs | PSNR-mu: 42.8893 -> 43.3528 | Improved |
| add pixel-level masking (ablation) | BL+MT+L^k · Kalantari 6.7% GTs | PSNR-mu: 42.8893 -> 43.2513 | Improved |
| use both patch- and pixel-level masking (ablation) | BL+MT+L^k · Kalantari 6.7% GTs | PSNR-mu: 42.8893 -> 43.4787 | Improved |
| add strong augmentations for pseudo-labeled training (ablation) | BL+MT+L^k+PaM+PiM · Kalantari 6.7% GTs | PSNR-mu: 43.4787 -> 44.0378 | Improved |
| use judge-network uncertainty instead of SMAE APSS scoring (ablation) | MT framework · Kalantari 6.7% GTs | PSNR-mu: 42.7956 -> 44.0378 | Improved |
| use mean-teacher masking strategy instead of FSHDR synthetic pseudo-labels (ablation) | BL · Kalantari 6.7% GTs | PSNR-mu: 43.5640 -> 44.0378 | Improved |
| apply semi-supervised method over GFHDR baseline | GFHDR · Kalantari 6.7% GTs | PSNR-mu: 42.72 -> 44.15 | Improved |
| increase labeled data from 6.7% to 27.0% | Ours · Kalantari | PSNR-mu: 44.15 -> 44.21 | No clear effect |
| use semi-supervised method with 6.7% labels vs supervised GFHDR with 100% labels | Ours · Kalantari | PSNR-mu: 44.32 -> 44.15 | Improved |
| apply semi-supervised method over GFHDR on Hu dataset | GFHDR · Hu | PSNR-mu: 42.97±0.17 -> 45.10±0.25 | Improved |
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.
- ADNet — ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment (ICCV 2021) · 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
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.88)
- HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.87)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.87)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.87)
- From Chaos to Clarity: 3DGS in the Dark (NeurIPS 2024 · similarity 0.87)
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.
