Research map / Vision-language and multimodal / Human and embodied modeling
Empowering Semantic-Sensitive Underwater Image Enhancement with VLM
Guodong Fan, Shengning Zhou, Genji Yuan, Huiyu Li, Jingchun Zhou, Jinjiang 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 |
|---|---|---|---|
| add VLM semantic-sensitive guidance (-SS) to UIE baselines | five UIE baselines · UIEB test | PSNR (dB): PUIE 21.05 -> 23.20; FDCE 23.66 -> 24.63 | Improved |
| add -SS to UIE baselines for no-reference quality | five UIE baselines · U45 and Challenge60 | UIQM/UCIQE: e.g. SMDR UIQM 2.727 -> 2.852 | Improved |
| enhance with -SS before segmentation | PFormer · SUIM segmentation | mIoU: 69.34 -> 74.75 | Improved |
| enhance with -SS before detection | FDCE · Trash-ICRA19 detection | mAP: 95.72 -> 97.01 | Improved |
| enhance with baseline PUIE instead of using raw images | PUIE · SUIM segmentation | mIoU: 68.10 -> 66.20 | Hurt |
| enhance with baseline PUIE instead of raw images for detection | PUIE · Trash-ICRA19 detection | mAP: 95.43 -> 95.40 | No clear effect |
| inject semantic guidance into decoder only vs encoder only or all stages (ablation) | -SS · UIEB / downstream | perceptual and downstream metrics | Improved |
| use BLIP for guidance map instead of ViT class attention or CLIP (ablation) | -SS · guidance map quality | qualitative | Improved |
Closest papers by meaning
- HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning (IJCV 2025 · similarity 0.89)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.87)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.86)
- Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement (AAAI 2024 · similarity 0.85)
- NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding (NeurIPS 2025 · similarity 0.85)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.85)
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.
