Research map / Image generation / Image restoration
Codebook-Empowered Analysis-Friendly Extreme Underwater Image Compression
JianHao Wu, Yudong Mao, Qiuping Jiang
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 codebook-driven feature extraction (CDFE) (ablation) | VQ-UIC (Ours) · SUIM-100 segmentation @ 0.04 bpp | mIoU: 48.03 -> 49.06 | Improved |
| add codebook-driven feature refinement (CDFR) (ablation) | VQ-UIC (Ours) · SUIM-100 segmentation @ 0.04 bpp | mIoU: 48.03 -> 54.30 | Improved |
| add CDFR (ablation) | VQ-UIC (Ours) · USOD-300 saliency @ 0.04 bpp | F-beta: 86.52 -> 91.83 | Improved |
| add CDFE on top of CDFR (ablation) | VQ-UIC (Ours) · SUIM-100 segmentation @ 0.04 bpp | mIoU: 54.30 -> 54.83 | Improved |
| add CDFE on top of CDFR (ablation) | VQ-UIC (Ours) · RUOD-500 detection @ 0.04 bpp | mAP: 38.9 -> 40.5 | Improved |
| use codebook framework vs ELIC | Ours · SUIM-100 segmentation @ 0.025 bpp | mIoU: 34.82 -> 47.29 | Improved |
| use codebook framework vs ELIC | Ours · UVQA (LLaVA-7B) @ 0.025 bpp | accuracy: 81.2 -> 82.4 | No clear effect |
| use codebook framework vs ELIC | Ours · USOD-300 saliency @ 0.025 bpp | F-beta: 89.88 -> 90.71 | Improved |
Closest papers by meaning
- Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset (ICML 2024 · similarity 0.84)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.84)
- Benchmarking and Enhancing VLM for Compressed Image Understanding (ICML 2026 · similarity 0.84)
- NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding (NeurIPS 2025 · similarity 0.84)
- Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement (AAAI 2024 · similarity 0.84)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.83)
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.
