Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Sample Relationship for Exposure Correction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ERL sample-relationship regularization to FECNet | FECNet · MSEC | average PSNR: 23.12 -> 23.15 | Helped |
| Add ERL sample-relationship regularization to FECNet | FECNet · SICE | average PSNR: 20.96 -> 21.22 | Helped |
| Add ERL sample-relationship regularization to FECNet | FECNet · MSEC overexposure | PSNR: 23.22 -> 23.18 | Hurt |
| Add ERL sample-relationship regularization to FECNet | FECNet · SICE | average SSIM: 0.6849 -> 0.6781 | Hurt |
| Add ERL sample-relationship regularization to ECLNet | ECLNet · MSEC | average PSNR: 22.57 -> 22.70 | Helped |
| Add ERL sample-relationship regularization to ECLNet | ECLNet · SICE | average PSNR: 20.65 -> 20.81 | Helped |
| Add ERL sample-relationship regularization to DRBN | DRBN · SICE | average PSNR: 17.65 -> 18.01 | Helped |
| Add ERL sample-relationship regularization to DRBN-ENC | DRBN-ENC · MSEC | average PSNR: 22.35 -> 22.67 | Helped |
| Add ERL sample-relationship regularization to DRBN-ENC | DRBN-ENC · SICE | average PSNR: 20.49 -> 20.78 | Helped |
| Add ERL to FECNet in the mixed enhancement task | FECNet · LOL | PSNR: 22.03 -> 21.08 | Hurt |
| Add ERL to FECNet in the mixed enhancement task | FECNet · SICE overexposure | PSNR: 19.78 -> 20.57 | Helped |
| Omit the BCM pretext task (ablation) | ERL with ECLNet · SICE | PSNR: 20.81 -> 20.76 | Hurt |
Closest papers by meaning
- Region-Aware Exposure Consistency Network for Mixed Exposure Correction (AAAI 2024 · similarity 0.87)
- Exposure-slot: Exposure-centric Representations Learning with Slot-in-Slot Attention for Region-aware Exposure Correction (CVPR 2025 · similarity 0.84)
- Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps (ICLR 2024 · similarity 0.84)
- Elucidating the Exposure Bias in Diffusion Models (ICLR 2024 · similarity 0.83)
- Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models (AAAI 2024 · similarity 0.83)
- CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction (AAAI 2025 · similarity 0.82)
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.