Light-Field View Synthesis Using A Convolutional Block Attention Module

Gul, M. Shahzeb Khan; Mukati, M. Umair; Bätz, Michel; Forchhammer, Søren; Keinert, Joachim

doi:10.1109/icip42928.2021.9506586

Cited by 14 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, this technique is employed to weight local and global feature descriptors that specifically focus on high-frequency details. Shahzeb Khan Gul et al [ 38 ] proposed a novel learning-based approach that utilizes an attention mechanism (AM) to synthesize novel views of a light-field image using a sparse set of input views (i.e., four corner views) captured by a camera array. To achieve final adaptive image refinement, they employed a residual convolutional block attention module (CBAM).…”

Section: Related Workmentioning

confidence: 99%

Automated highway pavement crack recognition under complex environment

Zhang,

Yan,

Zhang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Automated highway pavement crack recognition under complex environment

Zhang,

Yan,

Zhang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…The detection branch mainly comprises a feature aggregation module, a saliency map prediction module, and a saliency map fusion. Specifically, first, deep feature maps F 1 and F 2 , fusing motion and appearance cues, are scaled to the same size as feature layer F 3 after operations of 3 × 3 convolution, CABM attention [48], and feature upsampling, favorable for subsequent feature aggregation. Upsampling multiples of maps F 1 and F 2 are set to 4 and 2, respectively.…”

Section: Dynamic Feature Salient Detectmentioning

confidence: 99%

SFD-SLAM: a novel dynamic RGB-D SLAM based on saliency region detection

Gong,

Sun,

Zou

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In dynamic environments, several SLAM systems effectively utilize optical flow fields to distinguish dynamic from static feature points. Commonly, these systems leverage the amplitude information within the optical flow field to develop adaptive thresholding segmentation models for identifying dynamic scene regions. Nevertheless, designing adaptive thresholding models typically necessitates meticulous planning and extensive experimentation. This study introduces a dynamic RGBD SLAM system, SFD-SLAM, which innovates by employing a saliency detection network for the direct extraction of dynamic regions via scene flow. This approach notably streamlines the design process associated with conventional adaptive thresholding models. Furthermore, SFD-SLAM incorporates a geometric module that merges depth residuals with hyperpixel segmentation to enhance the refinement of the dynamic mask. This is followed by integration with FCM clustering for the precise identification of moving objects. The efficacy of SFD-SLAM is assessed using the widely recognized TUM dynamic dataset. Experimental results demonstrate that the proposed system surpasses DGFlow-SLAM, which relies on an adaptive thresholding model for dynamic target segmentation, in terms of trajectory accuracy. It also achieves comparable localization accuracy to DynaSLAM. Moreover, SFD-SLAM maintains robust tracking capabilities, even in scenarios where DynaSLAM experiences tracking loss, thereby augmenting the robustness of RGBD-SLAM in dynamic settings.

show abstract

“…Among the many attention models, CBAM is a lightweight feedforward convolutional neural network attention module that can be integrated into any CNN architecture for end-to-end training [22,23]. Figure 2a illustrates the CBAM structure, Figure 2b shows the channel attention, and Figure 2c indicates the spatial attention.…”

Section: Cbam In the Decodermentioning

confidence: 99%

A Medical Image Segmentation Method Based on Improved UNet 3+ Network

Hou

Wang

et al. 2023

Diagnostics

View full text Add to dashboard Cite

In recent years, segmentation details and computing efficiency have become more important in medical image segmentation for clinical applications. In deep learning, UNet based on a convolutional neural network is one of the most commonly used models. UNet 3+ was designed as a modified UNet by adopting the architecture of full-scale skip connections. However, full-scale feature fusion can result in excessively redundant computations. This study aimed to reduce the network parameters of UNet 3+ while further improving the feature extraction capability. First, to eliminate redundancy and improve computational efficiency, we prune the full-scale skip connections of UNet 3+. In addition, we use the attention module called Convolutional Block Attention Module (CBAM) to capture more essential features and thus improve the feature expression capabilities. The performance of the proposed model was validated by three different types of datasets: skin cancer segmentation, breast cancer segmentation, and lung segmentation. The parameters are reduced by about 36% and 18% compared to UNet and UNet 3+, respectively. The results show that the proposed method not only outperformed the comparison models in a variety of evaluation metrics but also achieved more accurate segmentation results. The proposed models have lower network parameters that enhance feature extraction and improve segmentation performance efficiently. Furthermore, the models have great potential for application in medical imaging computer-aided diagnosis.

show abstract

Light-Field View Synthesis Using A Convolutional Block Attention Module

Cited by 14 publications

References 26 publications

Automated highway pavement crack recognition under complex environment

Automated highway pavement crack recognition under complex environment

SFD-SLAM: a novel dynamic RGB-D SLAM based on saliency region detection

A Medical Image Segmentation Method Based on Improved UNet 3+ Network

Contact Info

Product

Resources

About