Research map / Image generation / Image restoration
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
Zeyuan Chen, Yangchao Wang, Yang Yang, Dong Liu
This paper tried a common change: Add a reconstruction / auxiliary loss
Add CLAHE reconstruction loss to the prior loss committee · Real hazy images · visual quality Improved
What 987 accepted papers report for this change
- 882 improved
- 41 no clear effect
- 20 mixed
- 44 hurt
- OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View Clustering ICML 2026 · add reconstruction loss L_rec · Scene-15 (aligned, 70% missing) · ACC: 32.4 -> 37.5Improved
- Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR ICML 2026 · add R-probe auxiliary loss · OCRBench · score: 714.0 -> 721.0Improved
- Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution ICML 2026 · add reconstruction loss on observed entries (joint vs missing-only supervision) · ETTh1 10% missing · Masked MAE: 0.2002 -> 0.1658Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 PSD fine-tuning with the prior loss committee on MSBDN | MSBDN · RTTS | NIQE: 3.154 -> 3.077 | Improved |
| Use PSD fine-tuning with the prior loss committee on MSBDN | MSBDN · RTTS | BRISQUE: 28.743 -> 25.239 | Improved |
| Use PSD fine-tuning with the prior loss committee on MSBDN | MSBDN · RTTS | NIMA: 4.1401 -> 4.3459 | Improved |
| Use PSD fine-tuning with the prior loss committee on MSBDN | MSBDN · RTTS | FADE: 1.363 -> 0.920 | Hurt |
| Use PSD dehazing before object detection | YOLOv3 on RTTS · RTTS | mAP (%): 65.16 -> 65.84 | Improved |
| Add CLAHE reconstruction loss to the prior loss committee (ablation) | PSD · Real hazy images | visual quality | Improved |
| Add DCP loss to the prior loss committee (ablation) | PSD · Real hazy images | visual quality | Improved |
| Add BCP loss to the prior loss committee (ablation) | PSD · Real hazy images | visual quality | Improved |
Closest papers by meaning
- Prompt-Based Test-Time Real Image Dehazing: A Novel Pipeline (ECCV 2024 · similarity 0.92)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.90)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.90)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.89)
- CoA: Towards Real Image Dehazing via Compression-and-Adaptation (CVPR 2025 · similarity 0.88)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · 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.
