paper-with-me

홈 › Papers

Two-Stage Teacher-Student Reliable Prior Learning for Robust Underwater Image Enhancement

2026-07-31 · Yifan Chen, Jiaming Liu, Ye Zheng, Zhe Sun, Tao Chen arxiv

Underwater image enhancement (UIE) aims to recover clear images from observations affected by wavelength-dependent absorption, scattering, and spatially nonuniform degradation. Although existing generative methods can handle complex degradations, severe information loss may lead to semantic drift in the restored results. To address this issue, we propose RPL-UIE, a two-stage teacher--student framework for reliable prior learning. In the teacher stage, the network learns reliable and complementary spatial priors characterizing appearance and photometric properties from paired degraded and reference images. In the student stage, the network takes only degraded images as input and learns to emulate the teacher's prior extraction capability, thereby providing more reliable restoration guidance for the enhancement process without requiring reference images at inference. To reduce the prior-learning discrepancy between the teacher and student models, we further develop Residual Prior Refinement Diffusion (RPRD) and Frequency-Aware Prior Residual Calibration (FPRC). RPRD uses the coarse priors as anchors and progressively predicts the necessary corrections in the residual space. FPRC retains stable low-frequency residual components and selectively modulates high-frequency detail residuals, producing calibrated priors to support high-quality reconstruction. Experiments on multiple UIE benchmarks demonstrate competitive restoration performance. Downstream underwater object detection and instance segmentation experiments further demonstrate the improved utility of enhanced images for visual perception, while tests on real-world data captured by a remotely operated vehicle (ROV) support the robustness and practical applicability of RPL-UIE.

📄 PDF Abstract BibTeX arXiv:2608.00137

Code (0)

등록된 구현이 없습니다.

Tasks

Instance SegmentationImage EnhancementObject Detection

Similar Papers 제목 키워드 기반

AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

2026-07-05 · Qizhe Wei, Yingping Liang, Shaodi You, Ying Fu arxiv

Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\tex…

Zero-shot Generalization

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning

2023-11-14 · Helan Hu, Shuzheng Si, Haozhe Zhao, Shuang Zeng 외

Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the t…

named-entity-recognitionNamed Entity RecognitionNER

Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold

2026-07-30 · Songshuo Lu, Zhi Chen, Yaohua Tang arxiv

A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should…

Reinforcement LearningMathematical ReasoningInstruction FollowingCode Generation

UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement

2024-08-20 · Yingtie Lei, JIA YU, Yihang Dong, Changwei Gong 외

Underwater image enhancement (UIE) plays a crucial role in various marine applications, but it remains challenging due to the complex underwater environment. Current learning-based approaches frequently lack explicit inc…

Image EnhancementUIEUnderwater Image Restoration

Adversarial Concept Distillation for One-Step Diffusion Personalization

2025-10-23 · Yixiong Yang, Tao Wu, Senmao Li, Shiqi Yang 외 arxiv

Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains challenging, as existing methods consis…