Research map / Detection and segmentation / CNN features
HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning
Zengxi Zhang, Zhiying Jiang, Long Ma, Jinyuan Liu, Xin Fan, Risheng Liu
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 style loss (ablation) | HUPE · UIEBD | visual contrast / quantitative metrics | Improved |
| add L1 and contrastive losses (ablation) | HUPE · UIEBD | visual color fidelity | Improved |
| add gradient and depth maps as inputs to the heuristic prior guided encoder (ablation) | HUPE · underwater scenes | brightness and contrast | Improved |
| include RGB image as encoder input (ablation) | HUPE · underwater scenes | visual brightness | Improved |
| add phase branch in spatial-frequency affine block (ablation) | HUPE · underwater scenes | scene reflection recovery | Improved |
| add amplitude branch in spatial-frequency affine block (ablation) | HUPE · underwater scenes | overall brightness | Improved |
| add frequency components (both amplitude and phase) (ablation) | HUPE · underwater scenes | color cast | Improved |
| use 3 hybrid invertible blocks instead of fewer than 3 (ablation) | HUPE · underwater scenes | all evaluation metrics: N<3 -> N=3 | Improved |
| increase hybrid invertible blocks beyond 3 (ablation) | HUPE · underwater scenes | image quality | No clear effect |
| use 6 flow steps instead of fewer than 4 (ablation) | HUPE · underwater scenes | color balance | Improved |
| increase flow steps beyond 6 (ablation) | HUPE · underwater scenes | quantitative metrics | No clear effect |
| add semantic collaborative learning instead of traditional cascade (HUPE-CS) (ablation) | HUPE · RUIE/Aquarium detection and SUIM segmentation | AP / IoU | Improved |
Closest papers by meaning
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.88)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.87)
- WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration (AAAI 2025 · similarity 0.86)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.85)
- 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 0.84)
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.
