Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.

The Devil is in the Decoder: Classification, Regression and GANs

Abstract: Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. This paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise tasks ranging from classification, regression to synthesis. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce new residual-like connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.

MultiBoot Vsr: Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution

Abstract: To make the best use of the previous estimations and shared redundancy across the consecutive video frames, here we propose a scene and class agnostic, fully convolutional neural network model for 4× video super-resolution. One stage of our network is composed of a motion compensation based input subnetwork, a blending backbone, and a spatial upsampling subnetwork. We recurrently apply this network to reconstruct high-resolution frames and then reuse them as additional reference frames after reshuffling them into multiple low-resolution images. This allows us to bootstrap and enhance image quality progressively. Our experiments show that our method generates temporally consistent and high-quality results without artifacts. Our method is ranked as the second best based on the SSIM scores on the NTIRE2019 VSR Challenge, Clean Track.

FENet: feature enhancement network for land cover classification

Abstract: ABSTRACT Extracting mask information of buildings and water areas from high resolution remote sensing images is beneficial to monitoring and management of urban development. However, due to different times, different geographical locations and different remote sensing acquisition angles, water areas and buildings will feed back different spectral information. Existing semantic segmentation methods do not pay enough attention to channel information, and the feature information extracted by downsampling is relatively abstract, which is easy to cause the loss of some details in high-resolution images under complex scenes, leading to the misjudgement of buildings and waters. To solve the existing problems, feature enhancement network (FENet) for high-resolution remote sensing image segmentation of buildings and water areas is proposed. By paying more attention to the characteristic information of the passage, the probability of misjudgement of buildings and waters can be reduced and their edge contour information can be enhanced. The self-attention feature module proposed in this paper encodes the context information and transmits it to the local features, and establishes the relationship between channels through the channel feature enhancement module to reduce the loss of channel feature information. The feature fusion module fuses feature information of different scales in space and outputs more detailed prediction images. Comparative experiments show that this model is superior to the existing classical semantic segmentation model. Compared with the existing models, the proposed method can achieve 2% improvement than PSPNet on the indicator MIoU, and the final MIoU reaches 82.85% for land cover dataset. This study demonstrates the advantages of our proposed method in land cover classification and detection.

Super-Resolution ISAR Imaging for Maneuvering Target Based on Deep-Learning-Assisted Time–Frequency Analysis

Abstract: Traditional range-instantaneous Doppler (RID) methods for maneuvering target imaging suffer from the problems of low resolution and poor noise suppression. We propose a new super-resolution inverse synthetic aperture radar (ISAR) imaging method based on deep-learning-assisted time–frequency analysis (TFA). Our deep neural network resembles the basic structure of a U-net with two additional convolutional-upsampling layers and $l_{1}$ -norm loss function for super-resolution generation and noise suppression. The neural network is trained in advance to learn the mapping function between the low-resolution time–frequency spectrum inputs and their high-resolution references. Then, the linear TFA assisted by the pretrained network is integrated into the RID-based ISAR imaging system and is found to achieve sharply focused and denoised target image with super-resolution. Both the simulated and real radar data are used to evaluate the performance of the proposed method. Numerical experimental results demonstrate the superiority of the proposed ISAR imaging method over traditional ones.

Sample rate conversion module and applications thereof

Abstract: A sample rate converter includes an upsampling module, a low pass filter, and a linear sample rate conversion module. The upsampling module is operably coupled up-sample a digital input signal having a first rate to produce a digitally up-sampled signal. The low pass filter is operably coupled to low pass filter the digitally up-sampled signal to produce a digitally filtered signal at an up-sampled rate. The linear sample rate conversion module is operably coupled to convert the digitally up-sampled signal into a sample rate adjusted digital signal having a second rate based on an control feedback signal and a linear function, wherein a relationship between the first rate and the second rate is a non-power of two.