Upsampling

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

Change Detection of Remote Sensing Images Based on Attention Mechanism.

Abstract: In recent years, image processing methods based on convolutional neural networks (CNNs) have achieved very good results. At the same time, many branch techniques have been proposed to improve accuracy. Aiming at the change detection task of remote sensing images, we propose a new network based on U-Net in this paper. The attention mechanism is cleverly applied in the change detection task, and the data-dependent upsampling (DUpsampling) method is used at the same time, so that the network shows improvement in accuracy, and the calculation amount is greatly reduced. The experimental results show that, in the two-phase images of Yinchuan City, the proposed network has a better antinoise ability and can avoid false detection to a certain extent.

A unified approach to restoration, deinterlacing and resolution enhancement in decoding MPEG-2 video

Abstract: The quality and spatial resolution of video can be improved by combining multiple pictures to form a single superresolution picture. We address the special problems associated with pictures of variable but somehow parameterized quality such as MPEG-decoded video. Our algorithm provides a unified approach to restoration, chrominance upsampling, deinterlacing, and resolution enhancement. A decoded MPEG-2 sequence for interlaced standard definition television (SDTV) in 4:2:0 is converted to: (1) improved quality interlaced SDTV in 4:2:0; (2) interlaced SDTV in 4:4:4; (3) progressive SDTV in 4:4:4; (4) interlaced high-definition TV (HDTV) in 4:2:0; (5) progressive HDTV in 4:2:0. These conversions also provide features such as freeze frame and zoom. The algorithm is mainly targeted at bit rates of 4-8 Mb/s. The algorithm is based on motion-compensated spatial upsampling from multiple images and decimation to the desired format. The processing involves an estimated quality of individual pixels based on MPEG image type and local quantization value. The mean-squared error (MSE) is reduced, compared to the directly decoded sequence, and annoying ringing artifacts, including mosquito noise, are effectively suppressed. The superresolution pictures obtained by the algorithm are of much higher visual quality and have lower MSE than superresolution pictures obtained by simple spatial interpolation.

Image upsampling system, training method thereof and image upsampling method

Abstract: An image upsampling system, a training method thereof and an image upsampling method are provided, the feature images of an image are obtained by using the convolutional network, upsampling processing is performed on the images with the muxer layer to synthesize every n×n feature images in the input signal into a feature image with the resolution amplified by n×n times, in the upsampling procedure with the muxer layer, information of respective feature images in the input signal is recorded in the generated feature image(s) without loss; and thus, every time when the image passes through a muxer layer with an upsampling multiple of n, the image resolution can be increased by n×n times.

Learning Feature Aggregation for Deep 3D Morphable Models

Abstract: 3D morphable models are widely used for the shape representation of an object class in computer vision and graphics applications. In this work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a hierarchical structure to capture information at multiple scales. While great efforts have been made to design the convolution operator, how to best aggregate vertex features across hierarchical levels deserves further attention. In contrast to resorting to mesh decimation, we propose an attention based module to learn mapping matrices for better feature aggregation across hierarchical levels. Specifically, the mapping matrices are generated by a compatibility function of the keys and queries. The keys and queries are trainable variables, learned by optimizing the target objective, and shared by all data samples of the same object class. Our proposed module can be used as a train-only drop-in replacement for the feature aggregation in existing architectures for both downsampling and upsampling. Our experiments show that through the end-to-end training of the mapping matrices, we achieve state-of-the-art results on a variety of 3D shape datasets in comparison to existing morphable models.

Methods and apparatus for generating a filtered signal having a fixed sampling rate from a variable baud rate input data stream

Abstract: A sample stream having a fixed sampling rate, representing a filtered version of an input symbol stream is produced by a pulse shaping and resampling device of the present invention. The pulse shaping/resampling device can be used as part of a digital modulator. In order to accommodate a wide range of (“variable”) input baud rates, as part of the pulse shaping/resampling device, a filter having an integral upsampling ratio is used, followed by a resampler circuit having a finely adjustable resampling ratio. The resampler provides an average output rate equal to the desired fixed sampling rate. In various embodiments it is followed by a buffer, which smoothes the output to provide a uniform output rate equal to the desired fixed sampling rate. The pulse shaping/resampling circuit of the present invention may be used in place of a known pulse shaping circuit in a modulator to produce a modulator capable of supporting a wide range of input signal rates.