Research map / Image generation / Image restoration
Colorization for In Situ Marine Plankton Images
Guannan Guo, Qi Lin, Tao Chen, Zhenghui Feng, Zheng Wang, Jianping Li
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 |
|---|---|---|---|
| increase palette color clusters K from 32 to 64 or 128 (ablation) | IsPlanktonCLR palette · In situ plankton images | colorization quality: K=32, 64, 128 | No clear effect |
| use continuous instead of discrete encoding of color family label (ablation) | reference module · confusable plankton images | colorization quality | Improved |
| use continuous instead of discrete encoding of color family label (ablation) | reference module · most plankton images | colorization quality | No clear effect |
| add reference information via the combiner (ablation) | colorization module · In situ plankton images | activation map | Improved |
| use OHEM plus weighted focal loss instead of cross-entropy (ablation) | colorization training · In situ plankton images | convergence speed | Improved |
| use IsPlanktonCLR instead of LetColor | LetColor · Testing Set 1 | FID: 29.063 -> 24.578 | Improved |
| use IsPlanktonCLR instead of LetColor | LetColor · Testing Set 1 | CDSIM: 384.637 -> 346.434 | Improved |
| use IsPlanktonCLR instead of LetColor | LetColor · Testing Set 1 | Human score: 2.920 -> 3.785 | Improved |
| use IsPlanktonCLR instead of MemoColor | MemoColor · Testing Set 1 | Colorfulness: 6.789 -> 5.921 | Hurt |
| use IsPlanktonCLR instead of CIC | CIC · Testing Set 1 | SSIM: 0.997 -> 0.996 | No clear effect |
Closest papers by meaning
- Learning Underwater Image Enhancement Iteratively Without Reference Images (AAAI 2026 · similarity 0.84)
- Underwater Organism Color Fine-Tuning via Decomposition and Guidance (AAAI 2024 · similarity 0.84)
- Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (TPAMI 2020 · similarity 0.84)
- Sea-Thru: A Method for Removing Water From Underwater Images (CVPR 2019 · similarity 0.84)
- Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion (CVPR 2024 · similarity 0.80)
- Sea-ing in Low-light (CVPR 2025 · similarity 0.80)
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.
