In this paper, we propose a compressed multi-scale feature fusion (MSFF) network for single image SR.
This process consists of three sequential phases: a multi-scale feature extraction, a scale prototype pattern generation, and a multi-scale prototype fusion pattern classification.
At the stage of feature extraction, we propose a scheme of multi-scale feature mapping to extract the inherent features via the low-resolution image.
Furthermore, we devise a technique for multi-scale feature abstraction using deeply supervised branches which are connected to all convolutional layers of the multi-stream CNN.
We then propose a raft cultivation area (RCA) extraction method for high spatial resolution (HSR) remote sensing imagery based on multi-scale feature fusion and spatial rule induction.
With the help of Fast Fourier Transform (FFT), it is found that the autumn PWV in Chengdu region has a multi-scale feature, which includes a seasonal cycle, 22.5 days period (quasi-tri-weekly oscillation).
Our method of segmentation starts with a multi-scale feature detection, describing surface roughness and curvature around each 3D point, and is followed by seed finding and region growing steps.
The Gabor representation of face images incorporates multi-scale feature extraction.
Given a pair of range images RI a and RI b, the first step in the pipeline applies a multi-scale feature extraction method thoroughly described in Section "Feature extraction", such that meaningful points MP a and MP b are identified on the respective surfaces.
Moreover, the multi-scale features are elaborately designed, comprising of gray histogram and multi-scale total variation.
It uses 1D data, filters and a multi-branch architecture for separate training of multi-scale features.
