A5072913037- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Video Analysis and Summarization
- Visual Attention and Saliency Detection
- Video Surveillance and Tracking Methods
- Photoacoustic and Ultrasonic Imaging
- Image Retrieval and Classification Techniques
- Remote-Sensing Image Classification
- Image and Signal Denoising Methods
- Human Pose and Action Recognition
China University of Petroleum, East China
2021-2024
Wuhan University
2024
Underwater imaging often suffers from significant visual degradation, which limits its suitability for subsequent applications. While recent underwater image enhancement (UIE) methods rely on the current advances in deep neural network architecture designs, there is still considerable room improvement terms of cross-scene robustness and computational efficiency. Diffusion models have shown great success generation, prompting us to consider their application UIE tasks. However, directly...
Underwater salient object detection (USOD) plays a pivotal role in various vision-based marine exploration tasks. However, existing USOD techniques face the dilemma of mislocalization and imprecise boundaries due to complex underwater environment. The quality degradation raw images (caused by selective absorption medium scattering) makes it challenging perform instance directly. One conceivable approach involves initially removing visual disturbances through image enhancement (UIE), followed...
This paper presents a comprehensive underwater visual reconstruction paradigm that comprises three procedures, i.e., the E-procedure, R-procedure, and H-procedure. The E-procedure enhances original images based on color compensation balance weighted image fusion, yielding restored color, sharpened edges, global contrast. R-procedure registers multiple enhanced by exploiting similarity local deformation. H-procedure homogenizes registered multi-scale composition strategy, which eliminates...
Recent advances in satellite remote sensing technology and computer have significantly impacted practical applications image segmentation. However, the prevalent hybrid segmentation models that combine Convolutional Neural Networks (CNNs) Transformers, often overlook critical exploration of local global feature correlations across various scales. This is essential for learning more representative features strengthening context modeling capabilities. Additionally, decoding layers these do not...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI