superresolution   50

[v 0 .95] Doom Neural Upscale 2X - WADs & Mods - Doomworld
Using AI NeuralNetworks (A lot of Nividia's texture tools super resolution and a little bit of Topaz's AI gigaPixel), all textures and sprites have been upscaled 8x (with tons of AI artefacts), then downscaled to a final 2X to restore a pixel art look.
doom  upscale  neuralnetwork  ai  superresolution  topaz  gigapixel 
december 2018 by danhon
In 2010 I made a small video demonstrating analysis by using a movie of the Eiffel Tower at night…
SuperResolution  from twitter_favs
november 2018 by rukku
[1710.06647] Image Restoration by Iterative Denoising and Backward Projections
Inverse problems appear in many applications such as image deblurring and inpainting. The common approach to address them is to design a specific algorithm for each problem. The Plug-and-Play (P&P) framework, which has been recently introduced, allows solving general inverse problems by leveraging the impressive capabilities of existing denoising algorithms. While this fresh strategy has found many applications, a burdensome parameter tuning is often required in order to obtain high-quality results. In this work, we propose an alternative method for solving inverse problems using denoising algorithms, which requires less parameter tuning. We provide a theoretical analysis of the method, and empirically demonstrate that it is competitive with task-specific techniques and the P&P approach for image inpainting and deblurring.
inverse-problems  image-processing  superresolution  algorithms  performance-measure  to-write-about  nudge-targets  consider:looking-to-see 
february 2018 by Vaguery
[1710.01992] Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality.
superresolution  neural-networks  representation  algorithms  image-processing  generative-models  to-write-about  nudge-targets  consider:representation  consider:performance-measures 
november 2017 by Vaguery
[1707.05425] Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
We propose a highly efficient and faster Single Image Super-Resolution (SISR) model with Deep Convolutional neural networks (Deep CNN). Deep CNN have recently shown that they have a significant reconstruction performance on single-image super-resolution. Current trend is using deeper CNN layers to improve performance. However, deep models demand larger computation resources and is not suitable for network edge devices like mobile, tablet and IoT devices. Our model achieves state of the art reconstruction performance with at least 10 times lower calculation cost by Deep CNN with Residual Net, Skip Connection and Network in Network (DCSCN). A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area. Parallelized 1x1 CNNs, like the one called Network in Network, is also used for image reconstruction. That structure reduces the dimensions of the previous layer's output for faster computation with less information loss, and make it possible to process original images directly. Also we optimize the number of layers and filters of each CNN to significantly reduce the calculation cost. Thus, the proposed algorithm not only achieves the state of the art performance but also achieves faster and efficient computation. Code is available at this https URL
superresolution  image-processing  deep-learning  neural-networks  generative-models  nudge-targets  consider:representation 
november 2017 by Vaguery
a simple nearest-neighbor (NN) approach that synthesizes high-frequency photorealistic images from an "incomplete" signal such as a low-resolution image, a surface normal map, or edges.
superresolution  imageprocessing 
september 2017 by Z303
RT : Just published , a new approach in for most microscopes
superresolution  SRRF  from twitter
april 2017 by shaneisley
[1702.02680] Manifold Based Low-rank Regularization for Image Restoration and Semi-supervised Learning
Low-rank structures play important role in recent advances of many problems in image science and data science. As a natural extension of low-rank structures for data with nonlinear structures, the concept of the low-dimensional manifold structure has been considered in many data processing problems. Inspired by this concept, we consider a manifold based low-rank regularization as a linear approximation of manifold dimension. This regularization is less restricted than the global low-rank regularization, and thus enjoy more flexibility to handle data with nonlinear structures. As applications, we demonstrate the proposed regularization to classical inverse problems in image sciences and data sciences including image inpainting, image super-resolution, X-ray computer tomography (CT) image reconstruction and semi-supervised learning. We conduct intensive numerical experiments in several image restoration problems and a semi-supervised learning problem of classifying handwritten digits using the MINST data. Our numerical tests demonstrate the effectiveness of the proposed methods and illustrate that the new regularization methods produce outstanding results by comparing with many existing methods.
image-processing  superresolution  rather-interesting  inference  learning-from-data  algorithms  nudge-targets  consider:feature-discovery  consider:looking-to-see 
february 2017 by Vaguery
[1612.08278] Photoacoustic imaging beyond the acoustic diffraction-limit with dynamic speckle illumination and sparse joint support recovery
In deep tissue photoacoustic imaging the spatial resolution is inherently limited by the acoustic wavelength. Recently, it was demonstrated that it is possible to surpass the acoustic diffraction limit by analyzing fluctuations in a set of photoacoustic images obtained under unknown speckle illumination patterns. Here, we purpose an approach to boost reconstruction fidelity and resolution, while reducing the number of acquired images by utilizing a compressed sensing computational reconstruction framework. The approach takes into account prior knowledge of the system response and sparsity of the target structure. We provide proof of principle experiments of the approach and demonstrate that improved performance is obtained when both speckle fluctuations and object priors are used. We numerically study the expected performance as a function of the measurements signal to noise ratio and sample spatial-sparsity. The presented reconstruction framework can be applied to analyze existing photoacoustic experimental datasets containing dynamic fluctuations.
data-fusion  superresolution  rather-interesting  to-understand  signal-processing  compressed-sensing  nudge-targets  consider:representation 
january 2017 by Vaguery
[1609.05158] Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.
superresolution  image-processing  machine-learning  algorithms  nudge-targets  consider:representation  consider:looking-to-see 
january 2017 by Vaguery

related tags

ai  algorithm  algorithms  article  audio  awesome  cg  cnn  code  compressed-sensing  computervision  consider:feature-discovery  consider:looking-to-see  consider:nonlinearity  consider:performance-measures  consider:rediscovery  consider:representation  cv  data-fusion  deep-learning  deep_learning  deeplearning  discussion  dl  dnn  doom  ecommerce  enhance  feature-construction  generative-models  gigapixel  gimp  graphics  iclr  image-processing  image  image_processing  imageprocessing  images  imaging  inference  information-theory  interesting  interpolation  invention  inverse-problems  learning-from-data  likely  loss  machine-learning  machinelearning  metamaterials  microscopy  ml  neural-networks  neuralnet  neuralnetwork  nn  nudge-targets  opencv  opensource  optics  optimization  paper  papers  perceptual  performance-measure  photo  photography  physics  programming  python  rather-interesting  representation  research  resizing  resolution  review  science  signal-processing  software  srrf  statistics  stitching  styletransfer  super-resolution  tensorflow  to-understand  to-write-about  tools  topaz  upscale  video  virtualdub  vision 

Copy this bookmark: