No abstract

No abstract

Single image rain streaks removal is extremely important since rainy images adversely a ect many computer vision systems. Deep learning based methods have found great success in image deraining tasks. In this paper, we propose a novel residual-guide feature fusion network, called ResGuideNet, for single image deraining that progressively predicts high-quality reconstruction. Speci cally, we propose a cascaded network and adopt residuals generated from shallower blocks to guide deeper blocks. By using this strategy, we can obtain a coarse to ne estimation of negative residual as the blocks go deeper. e outputs of di erent blocks are merged into the nal reconstruction. We adopt recursive convolution to build each block and apply supervision to all intermediate results, which enable our model to achieve promising performance on synthetic and real-world data while using fewer parameters than previous required. ResGuideNet is detachable to meet di erent rainy conditions. For images with light rain streaks and limited computational resource at test time, we can obtain a decent performance even with several building blocks. Experiments validate that ResGuideNet can bene t other low-and high-level vision tasks.

No abstract

The need for fast acquisition and automatic analysis of MRI data is growing in the age of big data. Although compressed sensing magnetic resonance imaging (CS-MRI) has been studied to accelerate MRI by reducing k-space measurements, in current CS-MRI techniques MRI applications such as segmentation are overlooked when doing image reconstruction. In this paper, we test the utility of CS-MRI methods in automatic segmentation models and propose a unified deep neural network architecture called SegNetMRI which we apply to the combined CS-MRI reconstruction and segmentation problem. SegNetMRI is built upon a MRI reconstruction network with multiple cascaded blocks each containing an encoder-decoder unit and a data fidelity unit, and MRI segmentation networks having the same encoder-decoder structure. The two subnetworks are pre-trained and finetuned with shared reconstruction encoders. The outputs are merged into the final segmentation. Our experiments show that SegNetMRI can improve both the reconstruction and segmentation performance when using compressive measurements.