Showing papers on "Upsampling published in 2018"

Understanding Convolution for Semantic Segmentation

Abstract: Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we show how to improve pixel-wise semantic segmentation by manipulating convolution-related operations that are of both theoretical and practical value. First, we design dense upsampling convolution (DUC) to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling. Second, we propose a hybrid dilated convolution (HDC) framework in the encoding phase. This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue"caused by the standard dilated convolution operation. We evaluate our approaches thoroughly on the Cityscapes dataset, and achieve a state-of-art result of 80.1% mIOU in the test set at the time of submission. We also have achieved state-of-theart overall on the KITTI road estimation benchmark and the PASCAL VOC2012 segmentation task. Our source code can be found at https://github.com/TuSimple/TuSimple-DUC.

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

Abstract: Video super-resolution (VSR) has become even more important recently to provide high resolution (HR) contents for ultra high definition displays. While many deep learning based VSR methods have been proposed, most of them rely heavily on the accuracy of motion estimation and compensation. We introduce a fundamentally different framework for VSR in this paper. We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation. With our approach, an HR image is reconstructed directly from the input image using the dynamic upsampling filters, and the fine details are added through the computed residual. Our network with the help of a new data augmentation technique can generate much sharper HR videos with temporal consistency, compared with the previous methods. We also provide analysis of our network through extensive experiments to show how the network deals with motions implicitly.

PU-Net: Point Cloud Upsampling Network

Abstract: Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of features, which are then reconstructed to an upsampled point set. Our network is applied at a patch-level, with a joint loss function that encourages the upsampled points to remain on the underlying surface with a uniform distribution. We conduct various experiments using synthesis and scan data to evaluate our method and demonstrate its superiority over some baseline methods and an optimization-based method. Results show that our upsampled points have better uniformity and are located closer to the underlying surfaces.

Object Classification Using CNN-Based Fusion of Vision and LIDAR in Autonomous Vehicle Environment

Abstract: This paper presents an object classification method for vision and light detection and ranging (LIDAR) fusion of autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image upsampling theory. By creating a point cloud of LIDAR data upsampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is also adopted to guarantee both object classification accuracy and minimal loss. Experimental results are presented and show the effectiveness and efficiency of object classification strategies.

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction

Abstract: This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A key insight of this paper is that the network achieves a sub-pixel matching precision than is a magnitude higher than those of traditional stereo matching approaches. This allows us to achieve real-time performance by using a very low resolution cost volume that encodes all the information needed to achieve high disparity precision. Spatial precision is achieved by employing a learned edge-aware upsampling function. Our model uses a Siamese network to extract features from the left and right image. A first estimate of the disparity is computed in a very low resolution cost volume, then hierarchically the model re-introduces high-frequency details through a learned upsampling function that uses compact pixel-to-pixel refinement networks. Leveraging color input as a guide, this function is capable of producing high-quality edge-aware output. We achieve compelling results on multiple benchmarks, showing how the proposed method offers extreme flexibility at an acceptable computational budget.

Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network

Abstract: The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance – GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40 → 20 m, respectively 360 → 60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD.

A Fully Progressive Approach to Single-Image Super-Resolution

Abstract: Recent deep learning approaches to single image superresolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8×) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge [35]. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster.

Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

Abstract: Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and avoids fixed spectral transformations. Due to high sampling rates for audio, employing a long temporal input context on the sample level is difficult, but required for high quality separation results because of long-range temporal correlations. In this context, we propose the Wave-U-Net, an adaptation of the U-Net to the one-dimensional time domain, which repeatedly resamples feature maps to compute and combine features at different time scales. We introduce further architectural improvements, including an output layer that enforces source additivity, an upsampling technique and a context-aware prediction framework to reduce output artifacts. Experiments for singing voice separation indicate that our architecture yields a performance comparable to a state-of-the-art spectrogram-based U-Net architecture, given the same data. Finally, we reveal a problem with outliers in the currently used SDR evaluation metrics and suggest reporting rank-based statistics to alleviate this problem.

Fast End-to-End Trainable Guided Filter

Abstract: Image processing and pixel-wise dense prediction have been advanced by harnessing the capabilities of deep learning. One central issue of deep learning is the limited capacity to handle joint upsampling. We present a deep learning building block for joint upsampling, namely guided filtering layer. This layer aims at efficiently generating the high-resolution output given the corresponding low-resolution one and a high-resolution guidance map. The proposed layer is composed of a guided filter, which is reformulated as a fully differentiable block. To this end, we show that a guided filter can be expressed as a group of spatial varying linear transformation matrices. This layer could be integrated with the convolutional neural networks (CNNs) and jointly optimized through end-to-end training. To further take advantage of end-to-end training, we plug in a trainable transformation function that generates task-specific guidance maps. By integrating the CNNs and the proposed layer, we form deep guided filtering networks. The proposed networks are evaluated on five advanced image processing tasks. Experiments on MIT-Adobe FiveK Dataset demonstrate that the proposed approach runs 10-100A— faster and achieves the state-of-the-art performance. We also show that the proposed guided filtering layer helps to improve the performance of multiple pixel-wise dense prediction tasks. The code is available at https://github.com/wuhuikai/DeepGuidedFilter.

Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes

Abstract: Given a tiny face image, existing face hallucination methods aim at super-resolving its high-resolution (HR) counterpart by learning a mapping from an exemplar dataset. Since a low-resolution (LR) input patch may correspond to many HR candidate patches, this ambiguity may lead to distorted HR facial details and wrong attributes such as gender reversal. An LR input contains low-frequency facial components of its HR version while its residual face image, defined as the difference between the HR ground-truth and interpolated LR images, contains the missing high-frequency facial details. We demonstrate that supplementing residual images or feature maps with additional facial attribute information can significantly reduce the ambiguity in face super-resolution. To explore this idea, we develop an attribute-embedded upsampling network, which consists of an upsampling network and a discriminative network. The upsampling network is composed of an autoencoder with skip-connections, which incorporates facial attribute vectors into the residual features of LR inputs at the bottleneck of the autoencoder and deconvolutional layers used for upsampling. The discriminative network is designed to examine whether super-resolved faces contain the desired attributes or not and then its loss is used for updating the upsampling network. In this manner, we can super-resolve tiny (16A—16 pixels) unaligned face images with a large upscaling factor of 8A— while reducing the uncertainty of one-to-many mappings remarkably. By conducting extensive evaluations on a large-scale dataset, we demonstrate that our method achieves superior face hallucination results and outperforms the state-of-the-art.

HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images

Abstract: Hyperspectral recovery from a single RGB image has seen a great improvement with the development of deep convolutional neural networks (CNNs). In this paper, we propose two advanced CNNs for the hyperspectral reconstruction task, collectively called HSCNN+. We first develop a deep residual network named HSCNN-R, which comprises a number of residual blocks. The superior performance of this model comes from the modern architecture and optimization by removing the hand-crafted upsampling in HSCNN. Based on the promising results of HSCNN-R, we propose another distinct architecture that replaces the residual block by the dense block with a novel fusion scheme, leading to a new network named HSCNN-D. This model substantially deepens the network structure for a more accurate solution. Experimental results demonstrate that our proposed models significantly advance the state-of-the-art. In the NTIRE 2018 Spectral Reconstruction Challenge, our entries rank the 1st (HSCNN-D) and 2nd (HSCNN-R) places on both the "Clean" and "Real World" tracks. (Codes are available at [clean-r], [realworld-r], [clean-d], and [realworld-d].)

Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

Abstract: Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and avoids fixed spectral transformations. Due to high sampling rates for audio, employing a long temporal input context on the sample level is difficult, but required for high quality separation results because of long-range temporal correlations. In this context, we propose the Wave-U-Net, an adaptation of the U-Net to the one-dimensional time domain, which repeatedly resamples feature maps to compute and combine features at different time scales. We introduce further architectural improvements, including an output layer that enforces source additivity, an upsampling technique and a context-aware prediction framework to reduce output artifacts. Experiments for singing voice separation indicate that our architecture yields a performance comparable to a state-of-the-art spectrogram-based U-Net architecture, given the same data. Finally, we reveal a problem with outliers in the currently used SDR evaluation metrics and suggest reporting rank-based statistics to alleviate this problem.

ExpandNet : a deep convolutional neural network for high dynamic range expansion from low dynamic range content

Abstract: High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.

Robust Guided Image Filtering Using Nonconvex Potentials

Abstract: Filtering images using a guidance signal, a process called guided or joint image filtering, has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling. This uses an additional guidance signal as a structure prior, and transfers the structure of the guidance signal to an input image, restoring noisy or altered image structure. The main drawbacks of such a data-dependent framework are that it does not consider structural differences between guidance and input images, and that it is not robust to outliers. We propose a novel SD (for static/dynamic) filter to address these problems in a unified framework, and jointly leverage structural information from guidance and input images. Guided image filtering is formulated as a nonconvex optimization problem, which is solved by the majorize-minimization algorithm. The proposed algorithm converges quickly while guaranteeing a local minimum. The SD filter effectively controls the underlying image structure at different scales, and can handle a variety of types of data from different sensors. It is robust to outliers and other artifacts such as gradient reversal and global intensity shift, and has good edge-preserving smoothing properties. We demonstrate the flexibility and effectiveness of the proposed SD filter in a variety of applications, including depth upsampling, scale-space filtering, texture removal, flash/non-flash denoising, and RGB/NIR denoising.

Ensembles of Densely-Connected CNNs with Label-Uncertainty for Brain Tumor Segmentation

Abstract: We introduce a new family of classifiers based on our previous DeepSCAN architecture, in which densely connected blocks of dilated convolutions are embedded in a shallow U-net-style structure of down/upsampling and skip connections. These networks are trained using a newly designed loss function which models label noise and uncertainty. We present results on the testing dataset of the Multimodal Brain Tumor Segmentation Challenge 2018.

A Fully Progressive Approach to Single-Image Super-Resolution

Abstract: Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8x) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge [34]. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster.

Stochastic Reconstruction of an Oolitic Limestone by Generative Adversarial Networks

Abstract: Stochastic image reconstruction is a key part of modern digital rock physics and material analysis that aims to create representative samples of microstructures for upsampling, upscaling and uncertainty quantification. We present new results of a method of three-dimensional stochastic image reconstruction based on generative adversarial neural networks (GANs). GANs are a family of unsupervised learning methods that require no a priori inference of the probability distribution associated with the training data. Thanks to the use of two convolutional neural networks, the discriminator and the generator, in the training phase, and only the generator in the simulation phase, GANs allow the sampling of large and realistic volumetric images. We apply a GAN-based workflow of training and image generation to an oolitic Ketton limestone micro-CT unsegmented gray-level dataset. Minkowski functionals calculated as a function of the segmentation threshold are compared between simulated and acquired images. Flow simulations are run on the segmented images, and effective permeability and velocity distributions of simulated flow are also compared. Results show that GANs allow a fast and accurate reconstruction of the evaluated image dataset. We discuss the performance of GANs in relation to other simulation techniques and stress the benefits resulting from the use of convolutional neural networks . We address a number of challenges involved in GANs, in particular the representation of the probability distribution associated with the training data.

Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries

Abstract: We address the problem of segmenting an object given a natural language expression that describes it. Current techniques tackle this task by either (i) directly or recursively merging linguistic and visual information in the channel dimension and then performing convolutions; or by (ii) mapping the expression to a space in which it can be thought of as a filter, whose response is directly related to the presence of the object at a given spatial coordinate in the image, so that a convolution can be applied to look for the object. We propose a novel method that integrates these two insights in order to fully exploit the recursive nature of language. Additionally, during the upsampling process, we take advantage of the intermediate information generated when downsampling the image, so that detailed segmentations can be obtained. We compare our method against the state-of-the-art approaches in four standard datasets, in which it surpasses all previous methods in six of eight of the splits for this task.

Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks

Abstract: Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements. This success can be attributed in part to their ability to represent and generate natural images well. Contrary to classical tools such as wavelets, image-generating deep neural networks have a large number of parameters---typically a multiple of their output dimension---and need to be trained on large datasets. In this paper, we propose an untrained simple image model, called the deep decoder, which is a deep neural network that can generate natural images from very few weight parameters. The deep decoder has a simple architecture with no convolutions and fewer weight parameters than the output dimensionality. This underparameterization enables the deep decoder to compress images into a concise set of network weights, which we show is on par with wavelet-based thresholding. Further, underparameterization provides a barrier to overfitting, allowing the deep decoder to have state-of-the-art performance for denoising. The deep decoder is simple in the sense that each layer has an identical structure that consists of only one upsampling unit, pixel-wise linear combination of channels, ReLU activation, and channelwise normalization. This simplicity makes the network amenable to theoretical analysis, and it sheds light on the aspects of neural networks that enable them to form effective signal representations.

Kramers-Kronig receiver operable without digital upsampling.

Abstract: The Kramers-Kronig (KK) receiver is capable of retrieving the phase information of optical single-sideband (SSB) signal from the optical intensity when the optical signal satisfies the minimum phase condition. Thus, it is possible to direct-detect the optical SSB signal without suffering from the signal-signal beat interference and linear transmission impairments. However, due to the spectral broadening induced by nonlinear operations in the conventional KK algorithm, it is necessary to employ the digital upsampling at the beginning of the digital signal processing (DSP). The increased number of samples at the DSP would hinder the real-time implementation of this attractive receiver. Hence, we propose a new DSP algorithm for KK receiver operable at 2 samples per symbol. We adopt a couple of mathematical approximations to avoid the use of nonlinear operations such as logarithm and exponential functions. By using the proposed algorithm, we demonstrate the transmission of 112-Gb/s SSB orthogonal frequency-division-multiplexed signal over an 80-km fiber link. The results show that the proposed algorithm operating at 2 samples per symbol exhibits similar performance to the conventional KK one operating at 6 samples per symbol. We also present the error analysis of the proposed algorithm for KK receiver in comparison with the conventional one.

ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content

Abstract: High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.

Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks

Abstract: Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements. This success can be attributed in part to their ability to represent and generate natural images well. Contrary to classical tools such as wavelets, image-generating deep neural networks have a large number of parameters---typically a multiple of their output dimension---and need to be trained on large datasets. In this paper, we propose an untrained simple image model, called the deep decoder, which is a deep neural network that can generate natural images from very few weight parameters. The deep decoder has a simple architecture with no convolutions and fewer weight parameters than the output dimensionality. This underparameterization enables the deep decoder to compress images into a concise set of network weights, which we show is on par with wavelet-based thresholding. Further, underparameterization provides a barrier to overfitting, allowing the deep decoder to have state-of-the-art performance for denoising. The deep decoder is simple in the sense that each layer has an identical structure that consists of only one upsampling unit, pixel-wise linear combination of channels, ReLU activation, and channelwise normalization. This simplicity makes the network amenable to theoretical analysis, and it sheds light on the aspects of neural networks that enable them to form effective signal representations.

Dense Semantic Labeling with Atrous Spatial Pyramid Pooling and Decoder for High-Resolution Remote Sensing Imagery

Abstract: Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, atrous spatial pyramid pooling (ASPP) and encoder-decoder are two successful ones. The former structure is able to extract multi-scale contextual information and multiple effective field-of-view, while the latter structure can recover the spatial information to obtain sharper object boundaries. In this study, we propose a more efficient fully convolutional network by combining the advantages from both structures. Our model utilizes the deep residual network (ResNet) followed by ASPP as the encoder and combines two scales of high-level features with corresponding low-level features as the decoder at the upsampling stage. We further develop a multi-scale loss function to enhance the learning procedure. In the postprocessing, a novel superpixel-based dense conditional random field is employed to refine the predictions. We evaluate the proposed method on the Potsdam and Vaihingen datasets and the experimental results demonstrate that our method performs better than other machine learning or deep learning methods. Compared with the state-of-the-art DeepLab_v3+ our model gains 0.4% and 0.6% improvements in overall accuracy on these two datasets respectively.

Guided Upsampling Network for Real-Time Semantic Segmentation

Abstract: Semantic segmentation architectures are mainly built upon an encoder-decoder structure. These models perform subsequent downsampling operations in the encoder. Since operations on high-resolution activation maps are computationally expensive, usually the decoder produces output segmentation maps by upsampling with parameters-free operators like bilinear or nearest-neighbor. We propose a Neural Network named Guided Upsampling Network which consists of a multiresolution architecture that jointly exploits high-resolution and large context information. Then we introduce a new module named Guided Upsampling Module (GUM) that enriches upsampling operators by introducing a learnable transformation for semantic maps. It can be plugged into any existing encoder-decoder architecture with little modifications and low additional computation cost. We show with quantitative and qualitative experiments how our network benefits from the use of GUM module. A comprehensive set of experiments on the publicly available Cityscapes dataset demonstrates that Guided Upsampling Network can efficiently process high-resolution images in real-time while attaining state-of-the art performances.

Deep EEG super-resolution: Upsampling EEG spatial resolution with Generative Adversarial Networks

Abstract: Electroencephalography (EEG) activity contains a wealth of information about what is happening within the human brain. Recording more of this data has the potential to unlock endless future applications. However, the cost of EEG hardware is increasingly expensive based upon the number of EEG channels being recorded simultaneously. We combat this problem in this paper by proposing a novel deep EEG super­resolution (SR) approach based on Generative Adversarial Networks (GANs). This approach can produce high spatial resolution EEG data from low resolution samples, by generating channel-wise upsampled data to effectively interpolate numerous missing channels, thus reducing the need for expensive EEG equipment. We tested the performance using an EEG dataset from a mental imagery task. Our proposed GAN model provided ∼104 fold and ∼102 fold reduction in mean-squared error (MSE) and mean-absolute error (MAE), respectively, over the baseline bicubic interpolation method. We further validate our method by training a classifier on the original classification task, which displayed minimal loss in accuracy while using the super-resolved data. The proposed SR EEG by GAN is a promising approach to improve the spatial resolution of low density EEG headset.

Recurrent Multiresolution Convolutional Networks for VHR Image Classification

Abstract: Classification of very high-resolution (VHR) satellite images has three major challenges: 1) inherent low intraclass and high interclass spectral similarities; 2) mismatching resolution of available bands; and 3) the need to regularize noisy classification maps. Conventional methods have addressed these challenges by adopting separate stages of image fusion, feature extraction, and postclassification map regularization. These processing stages, however, are not jointly optimizing the classification task at hand. In this paper, we propose a single-stage framework embedding the processing stages in a recurrent multiresolution convolutional network trained in an end-to-end manner. The feedforward version of the network, called FuseNet , aims to match the resolution of the panchromatic and multispectral bands in a VHR image using convolutional layers with corresponding downsampling and upsampling operations. Contextual label information is incorporated into FuseNet by means of a recurrent version called ReuseNet . We compared FuseNet and ReuseNet against the use of separate processing steps for both image fusions, e.g., pansharpening and resampling through interpolation and map regularization such as conditional random fields . We carried out our experiments on a land-cover classification task using a Worldview-03 image of Quezon City, Philippines, and the International Society for Photogrammetry and Remote Sensing 2-D semantic labeling benchmark data set of Vaihingen, Germany. FuseNet and ReuseNet surpass the baseline approaches in both the quantitative and qualitative results.

Method and system for generating multidimensional maps of a scene using a plurality of sensors of various types

Abstract: A system and method for generating a high-density three-dimensional (3D) map are disclosed. The system comprises acquiring at least one high density image of a scene using at least one passive sensor; acquiring at least one new set of distance measurements of the scene using at least one active sensor; acquiring a previously generated 3D map of the scene comprising a previous set of distance measurements; merging the at least one new set of distance measurements with the previous set of upsampled distance measurements, wherein merging the at least one new set of distance measurements further includes accounting for a motion transformation between a previous high-density image frame and the acquired high density image and the acquired distance measurements; and overlaying the new set of distance measurements on the high-density image via an upsampling interpolation, creating an output 3D map.

Patch-based Progressive 3D Point Set Upsampling

Abstract: We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-the-art learning-based and optimazation-based approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.

Accurate Spectral Super-Resolution from Single RGB Image Using Multi-scale CNN

Abstract: Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain. However, it is challenging to accurately reconstruct a high-dimensional continuous spectrum from three discrete intensity values at each pixel, since too much information is lost during the procedure where the latent hyperspectral image is downsampled (e.g., with \(\times \)10 scaling factor) in spectral domain to produce an RGB observation. To address this problem, we present a multi-scale deep convolutional neural network (CNN) to explicitly map the input RGB image into a hyperspectral image. Through symmetrically downsampling and upsampling the intermediate feature maps in a cascading paradigm, the local and non-local image information can be jointly encoded for spectral representation, ultimately improving the spectral reconstruction accuracy. Extensive experiments on a large hyperspectral dataset demonstrate the effectiveness of the proposed method.

Fast End-to-End Trainable Guided Filter

Abstract: Dense pixel-wise image prediction has been advanced by harnessing the capabilities of Fully Convolutional Networks (FCNs). One central issue of FCNs is the limited capacity to handle joint upsampling. To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map. Such a layer contains learnable parameters, which can be integrated with FCNs and jointly optimized through end-to-end training. To further take advantage of end-to-end training, we plug in a trainable transformation function for generating the task-specific guidance map. Based on the proposed layer, we present a general framework for pixel-wise image prediction, named deep guided filtering network (DGF). The proposed network is evaluated on five image processing tasks. Experiments on MIT-Adobe FiveK Dataset demonstrate that DGF runs 10-100 times faster and achieves the state-of-the-art performance. We also show that DGF helps to improve the performance of multiple computer vision tasks.