Pugan: Physical model-guided underwater image enhancement using gan with dual-discriminators

R Cong, W Yang, W Zhang, C Li… - … on Image Processing, 2023 - ieeexplore.ieee.org
Due to the light absorption and scattering induced by the water medium, underwater images
usually suffer from some degradation problems, such as low contrast, color distortion, and …

Sddnet: Style-guided dual-layer disentanglement network for shadow detection

R Cong, Y Guan, J Chen, W Zhang, Y Zhao… - Proceedings of the 31st …, 2023 - dl.acm.org
Despite significant progress in shadow detection, current methods still struggle with the
adverse impact of background color, which may lead to errors when shadows are present on …

Query-guided Prototype Evolution Network for Few-Shot Segmentation

R Cong, H Xiong, J Chen, W Zhang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Previous Few-Shot Segmentation (FSS) approaches exclusively utilize support features for
prototype generation, neglecting the specific requirements of the query. To address this, we …

SCFANet: Semantics and Context Feature Aggregation Network for 360° Salient Object Detection

Z He, F Shao, G Chen, X Chai… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
How to solve the problem of geometric distortion is the key for salient object detection (SOD)
in 360° omnidirectional images. Most of the current methods integrate global and local …

Distortion-aware Transformer in 360° Salient Object Detection

Y Zhao, L Zhao, Q Yu, L Sheng, J Zhang… - Proceedings of the 31st …, 2023 - dl.acm.org
With the emergence of VR and AR, 360° data attracts increasing attention from the computer
vision and multimedia communities. Typically, 360° data is projected into 2D ERP …

Distortion-aware Transformer in 360 {\deg} Salient Object Detection

Y Zhao, L Zhao, Q Yu, J Zhang, L Sheng… - arXiv preprint arXiv …, 2023 - arxiv.org
With the emergence of VR and AR, 360 {\deg} data attracts increasing attention from the
computer vision and multimedia communities. Typically, 360 {\deg} data is projected into 2D …

LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras

F Teng, J Zhang, J Liu, K Peng, X Cheng, Z Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Leveraging the rich information extracted from light field (LF) cameras is instrumental for
dense prediction tasks. However, adapting light field data to enhance Salient Object …

WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learning

G Wang, C Chen, A Hao, H Qin, DP Fan - arXiv preprint arXiv:2305.13901, 2023 - arxiv.org
To date, the widely adopted way to perform fixation collection in panoptic video is based on
a head-mounted display (HMD), where users' fixations are collected while wearing an HMD …

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection

H Liu, R Cong, H Li, Q Xu, Q Huang… - Forty-first International … - openreview.net
Preserving details and avoiding high computational costs are the two main challenges for
the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two …