paper-with-me

Papers

IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater

2023-12-12 · Jingchun Zhou, Qilin Gai, Kin-Man Lam, Xianping Fu

In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and object detection (OD) tasks. Currently, in-air image enhancement and detection methods have made notable progress, but their application in underwater conditions is limited due to the complexity and variability of these environments. Fine-tuning in-air models saves high overhead and has more optional reference work than building an underwater model from scratch. To address these issues, we design a transfer plugin with multiple priors for converting in-air models to underwater applications, named IA2U. IA2U enables efficient application in underwater scenarios, thereby improving performance in Underwater IE and OD. IA2U integrates three types of underwater priors: the water type prior that characterizes the degree of image degradation, such as color and visibility; the degradation prior, focusing on differences in details and textures; and the sample prior, considering the environmental conditions at the time of capture and the characteristics of the photographed object. Utilizing a Transformer-like structure, IA2U employs these priors as query conditions and a joint task loss function to achieve hierarchical enhancement of task-level underwater image features, therefore considering the requirements of two different tasks, IE and OD. Experimental results show that IA2U combined with an in-air model can achieve superior performance in underwater image enhancement and object detection tasks. The code will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2312.06955

Code (0)

등록된 구현이 없습니다.

Tasks

Image Enhancementobject-detectionObject Detection

Similar Papers 제목 키워드 기반

MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics

2025-03-12 · Shuguang Chu, Zebin Huang, Yutong Li, Mingwei Lin 외

This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments i…

BenchmarkingGPUreinforcement-learningReinforcement Learning+1

Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement

2026-06-14 · Haochen Hu, Yanrui Bin, Zhengyan Zhang, Minchen Wei 외 arxiv

The underwater images are captured within diverse water-medium conditions, leading to complex degradation, including color bias, low contrast, and blur effect. Recently, learning-based methods have demonstrated their pot…

Image EnhancementTransfer Learning

Learning Heavily-Degraded Prior for Underwater Object Detection

2023-08-24 · Chenping Fu, Xin Fan, Jiewen Xiao, Wanqi Yuan 외

Underwater object detection suffers from low detection performance because the distance and wavelength dependent imaging process yield evident image quality degradations such as haze-like effects, low visibility, and col…

Objectobject-detectionObject Detection

UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis

2025-03-14 · Md Abu Bakr Siddique, Vaishnav Ramesh, Junliang Liu, Piyush Singh 외

The concept of waterbody style transfer remains largely unexplored in the underwater imaging and vision literature. Traditional image style transfer (STx) methods primarily focus on artistic and photorealistic blending, …

Style Transfer

Exploring the Underwater World Segmentation without Extra Training

2025-11-11 · Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao 외 arxiv

Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited to terrestrial scenes. To bridge this gap, we introduce \t…