MNet: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
Most existing salient object detection methods mostly use U-Net or feature pyramid structure,
which simply aggregates feature maps of different scales, ignoring the uniqueness and …
which simply aggregates feature maps of different scales, ignoring the uniqueness and …
Rethinking feature mining for light field salient object detection
Light field salient object detection (LF SOD) has recently received increasing attention.
However, most current works typically rely on an individual focal stack backbone for feature …
However, most current works typically rely on an individual focal stack backbone for feature …
Spatial Attention-Guided Light Field Salient Object Detection Network with Implicit Neural Representation
X Zheng, Z Li, D Liu, X Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, many Light Field Salient Object Detection (LF SOD) methods have been
proposed. However, guaranteeing the integrality and recovering more high-frequency …
proposed. However, guaranteeing the integrality and recovering more high-frequency …
End-to-End Semantic Segmentation Utilizing Multi-scale Baseline Light Field
Semantic segmentation based on 4D light field (LF) images exhibits superior performance
by exploiting rich spatial and angular information. However, current methods only focus on …
by exploiting rich spatial and angular information. However, current methods only focus on …
Masked Generative Light Field Prompting for Pixel-Level Structure Segmentations
Pixel-level structure segmentations have attracted considerable attention, playing a crucial
role in autonomous driving within the metaverse and enhancing comprehension in light field …
role in autonomous driving within the metaverse and enhancing comprehension in light field …
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
F Teng, J Zhang, K Peng, Y Wang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Light field cameras are capable of capturing intricate angular and spatial details. This allows
for acquiring complex light patterns and details from multiple angles, significantly enhancing …
for acquiring complex light patterns and details from multiple angles, significantly enhancing …
Occlusion-aware Unsupervised Light Field Depth Estimation based on Muti-Scale GANs
W Yan, X Zhang, H Chen - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
The estimation of depth from 4D light field images is a fundamental problem for perceiving
and reconstructing environmental scenes. While learning-based methods have achieved …
and reconstructing environmental scenes. While learning-based methods have achieved …
Saliency information and mosaic based data augmentation method for densely occluded object recognition
Y Tong, X Luo, L Ma, S Xie, W Yang, Y Guo - Pattern Analysis and …, 2024 - Springer
Data augmentation methods are crucial to improve the accuracy of densely occluded object
recognition in the scene where the quantity and diversity of training images are insufficient …
recognition in the scene where the quantity and diversity of training images are insufficient …
[PDF][PDF] 自适应卷积注意力与掩码结构协同的显著目标检测
朱磊, 袁金垚, 王文武, 蔡小嫚 - 电子与信息学报, 2024 - jeit.ac.cn
显著目标检测(SOD) 旨在模仿人类视觉系统注意力机制和认知机制来自动提取场景中的显著
物体. 虽然现有基于卷积神经网络(CNN) 或Transformer 的模型不断刷新该领域方法的性能 …
物体. 虽然现有基于卷积神经网络(CNN) 或Transformer 的模型不断刷新该领域方法的性能 …
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras
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 …
dense prediction tasks. However, adapting light field data to enhance Salient Object …