Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching the predictions to the input observations, and (ii) matching the predictions to known priors. We propose Adversarial Inverse Graphics networks (AIGNs): weakly supervised neural network models that combine feedback from rendering their predictions, with distribution matching between their predictions and a collection of ground-truth factors. We apply AIGNs to 3D human pose estimation and 3D structure and egomotion estimation, and outperform models supervised by only paired annotations. We further apply AIGNs to facial image transformation using super-resolution and inpainting renderers, while deliberately adding biases in the ground-truth datasets. Our model seamlessly incorporates such biases, rendering input faces towards young, old, feminine, masculine or Tom Cruise-like equivalents (depending on the chosen bias), or adding lip and nose augmentations while inpainting concealed lips and noses.
Removal of noise from an image is an extensively studied problem in image processing. Indeed, the recent advent of sophisticated and highly effective denoising algorithms lead some to believe that existing methods are touching the ceiling in terms of noise removal performance. Can we leverage this impressive achievement to treat other tasks in image processing? Recent work has answered this question positively, in the form of the Plug-and-Play Prior ($P^3$) method, showing that any inverse problem can be handled by sequentially applying image denoising steps. This relies heavily on the ADMM optimization technique in order to obtain this chained denoising interpretation. Is this the only way in which tasks in image processing can exploit the image denoising engine? In this paper we provide an alternative, more powerful and more flexible framework for achieving the same goal. As opposed to the $P^3$ method, we offer Regularization by Denoising (RED): using the denoising engine in defining the regularization of the inverse problem. We propose an explicit image-adaptive Laplacian-based regularization functional, making the overall objective functional clearer and better defined. With a complete flexibility to choose the iterative optimization procedure for minimizing the above functional, RED is capable of incorporating any image denoising algorithm, treat general inverse problems very effectively, and is guaranteed to converge to the globally optimal result. We test this approach and demonstrate state-of-the-art results in the image deblurring and super-resolution problems.
Over the past decades, various super-resolution (SR) techniques have been developed to enhance the spatial resolution of digital images. Despite the great number of methodical contributions, there is still a lack of comparative validations of SR under practical conditions, as capturing real ground truth data is a challenging task. Therefore, current studies are either evaluated 1) on simulated data or 2) on real data without a pixel-wise ground truth. To facilitate comprehensive studies, this paper introduces the publicly available Super-Resolution Erlangen (SupER) database that includes real low-resolution images along with high-resolution ground truth data. Our database comprises image sequences with more than 20k images captured from 14 scenes under various types of motions and photometric conditions. The datasets cover four spatial resolution levels using camera hardware binning. With this database, we benchmark 15 single-image and multi-frame SR algorithms. Our experiments quantitatively analyze SR accuracy and robustness under realistic conditions including independent object and camera motion or photometric variations.
Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications. However, the inadequate network bandwidth often limits the spatial resolution of the transmitted video, which will heavily degrade the recognition reliability. We develop a novel framework to achieve robust emotion recognition from low bit rate video. While video frames are downsampled at the encoder side, the decoder is embedded with a deep network model for joint super-resolution (SR) and recognition. Notably, we propose a novel max-mix training strategy, leading to a single "One-for-All" model that is remarkably robust to a vast range of downsampling factors. That makes our framework well adapted for the varied bandwidths in real transmission scenarios, without hampering scalability or efficiency. The proposed framework is evaluated on the AVEC 2016 benchmark, and demonstrates significantly improved stand-alone recognition performance, as well as rate-distortion (R-D) performance, than either directly recognizing from LR frames, or separating SR and recognition.
The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or super-resolution methods may show visually pleasing results. However, applying each technique independently before matching is generally unprofitable because this naive series of procedures ignores the consistency between images. In this paper, we propose a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring. By reflecting a physical imaging process, we formulate a cost minimization problem and solve it using an alternating optimization technique. The experimental results on both synthetic and real videos show high-quality depth maps derived from severely degraded images that contrast the failures of naive multi-view stereo methods. Our proposed method also produces outstanding deblurred and super-resolved images unlike the independent application or combination of conventional video deblurring, super-resolution methods.
In recent years, much research has been conducted on image super-resolution (SR). To the best of our knowledge, however, few SR methods were concerned with compressed images. The SR of compressed images is a challenging task due to the complicated compression artifacts, while many images suffer from them in practice. The intuitive solution for this difficult task is to decouple it into two sequential but independent subproblems, i.e., compression artifacts reduction (CAR) and SR. Nevertheless, some useful details may be removed in CAR stage, which is contrary to the goal of SR and makes the SR stage more challenging. In this paper, an end-to-end trainable deep convolutional neural network is designed to perform SR on compressed images (CISRDCNN), which reduces compression artifacts and improves image resolution jointly. Experiments on compressed images produced by JPEG (we take the JPEG as an example in this paper) demonstrate that the proposed CISRDCNN yields state-of-the-art SR performance on commonly used test images and imagesets. The results of CISRDCNN on real low quality web images are also very impressive, with obvious quality enhancement. Further, we explore the application of the proposed SR method in low bit-rate image coding, leading to better rate-distortion performance than JPEG.
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 https://github.com/jiny2001/dcscn-super-resolution
3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast but low-resolution image acquisition and highly detailed but slow image acquisition. Fast imaging is required for targets that move to avoid motion artefacts. This is in particular difficult for fetal MRI. Spatially independent upsampling techniques, which are the state-of-the-art to address this problem, are error prone and disregard contextual information. In this paper we propose a context-sensitive upsampling method based on a residual convolutional neural network model that learns organ specific appearance and adopts semantically to input data allowing for the generation of high resolution images with sharp edges and fine scale detail. By making contextual decisions about appearance and shape, present in different parts of an image, we gain a maximum of structural detail at a similar contrast as provided by high-resolution data. We experiment on $145$ fetal scans and show that our approach yields an increased PSNR of $1.25$ $dB$ when applied to under-sampled fetal data \emph{cf.} baseline upsampling. Furthermore, our method yields an increased PSNR of $1.73$ $dB$ when utilizing under-sampled fetal data to perform brain volume reconstruction on motion corrupted captured data.
Super-resolution is a classical problem in image processing, with numerous applications to remote sensing image enhancement. Here, we address the super-resolution of irregularly-sampled remote sensing images. Using an optimal interpolation as the low-resolution reconstruction, we explore locally-adapted multimodal convolutional models and investigate different dictionary-based decompositions, namely based on principal component analysis (PCA), sparse priors and non-negativity constraints. We consider an application to the reconstruction of sea surface height (SSH) fields from two information sources, along-track altimeter data and sea surface temperature (SST) data. The reported experiments demonstrate the relevance of the proposed model, especially locally-adapted parametrizations with non-negativity constraints, to outperform optimally-interpolated reconstructions.
One of the solutions of depth imaging of moving scene is to project a static pattern on the object and use just a single image for reconstruction. However, if the motion of the object is too fast with respect to the exposure time of the image sensor, patterns on the captured image are blurred and reconstruction fails. In this paper, we impose multiple projection patterns into each single captured image to realize temporal super resolution of the depth image sequences. With our method, multiple patterns are projected onto the object with higher fps than possible with a camera. In this case, the observed pattern varies depending on the depth and motion of the object, so we can extract temporal information of the scene from each single image. The decoding process is realized using a learning-based approach where no geometric calibration is needed. Experiments confirm the effectiveness of our method where sequential shapes are reconstructed from a single image. Both quantitative evaluations and comparisons with recent techniques were also conducted.
In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution. We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems. We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution. In addition, we learn the mean-shift vector field using denoising autoencoders, and use it in a gradient descent approach to perform Bayes risk minimization. We demonstrate competitive results for noise-blind deblurring, super-resolution, and demosaicing.
Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. 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 speed and accuracy.
In this survey paper, we review recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, super-resolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions: Where does the training data come from? What is the architecture of the CNN? and How is the learning problem formulated and solved? We also bring together a few key theoretical papers that offer perspective on why CNNs are appropriate for inverse problems and point to some next steps in the field.
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.
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a specific person or objects in a category. Our approach models an image as a composition of label and latent attributes in a probabilistic model. By varying the fine-grained category label fed into the resulting generative model, we can generate images in a specific category with randomly drawn values on a latent attribute vector. Our approach has two novel aspects. First, we adopt a cross entropy loss for the discriminative and classifier network, but a mean discrepancy objective for the generative network. This kind of asymmetric loss function makes the GAN training more stable. Second, we adopt an encoder network to learn the relationship between the latent space and the real image space, and use pairwise feature matching to keep the structure of generated images. We experiment with natural images of faces, flowers, and birds, and demonstrate that the proposed models are capable of generating realistic and diverse samples with fine-grained category labels. We further show that our models can be applied to other tasks, such as image inpainting, super-resolution, and data augmentation for training better face recognition models.
Face verification and recognition problems have seen rapid progress in recent years, however recognition from small size images remains a challenging task that is inherently intertwined with the task of face super-resolution. Tackling this problem using multiple frames is an attractive idea, yet requires solving the alignment problem that is also challenging for low-resolution faces. Here we present a holistic system for multi-frame recognition, alignment, and superresolution of faces. Our neural network architecture restores the central frame of each input sequence additionally taking into account a number of adjacent frames and making use of sub-pixel movements. We present our results using the popular dataset for video face recognition (YouTube Faces). We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution.
Multi-frame image super-resolution (MISR) aims to fuse information in low-resolution (LR) image sequence to compose a high-resolution (HR) one, which is applied extensively in many areas recently. Different with single image super-resolution (SISR), sub-pixel transitions between multiple frames introduce additional information, attaching more significance to fusion operator to alleviate the ill-posedness of MISR. For reconstruction-based approaches, the inevitable projection of reconstruction errors from LR space to HR space is commonly tackled by an interpolation operator, however crude interpolation may not fit the natural image and generate annoying blurring artifacts, especially after fusion operator. In this paper, we propose an end-to-end fast upscaling technique to replace the interpolation operator, design upscaling filters in LR space for periodic sub-locations respectively and shuffle the filter results to derive the final reconstruction errors in HR space. The proposed fast upscaling technique not only reduce the computational complexity of the upscaling operation by utilizing shuffling operation to avoid complex operation in HR space, but also realize superior performance with fewer blurring artifacts. Extensive experimental results demonstrate the effectiveness and efficiency of the proposed technique, whilst, combining the proposed technique with bilateral total variation (BTV) regu-larization, the MISR approach outperforms state-of-the-art methods.
Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution. Encouraged by the recent success of Convolutional Neural Network (CNN) architectures in image classification, we propose a novel resolution-aware deep model which combines convolutional image super-resolution and convolutional fine-grained classification into a single model in an end-to-end manner. Extensive experiments on the Stanford Cars and Caltech-UCSD Birds 200-2011 benchmarks demonstrate that the proposed model consistently performs better than conventional convolutional net on classifying fine-grained object classes in low-resolution images.
Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.
Image restoration methods aim to recover the underlying clean image from corrupted observations. The Expected Patch Log-likelihood (EPLL) algorithm is a powerful image restoration method that uses a Gaussian mixture model (GMM) prior on the patches of natural images. Although it is very effective for restoring images, its high runtime complexity makes EPLL ill-suited for most practical applications. In this paper, we propose three approximations to the original EPLL algorithm. The resulting algorithm, which we call the fast-EPLL (FEPLL), attains a dramatic speed-up of two orders of magnitude over EPLL while incurring a negligible drop in the restored image quality (less than 0.5 dB). We demonstrate the efficacy and versatility of our algorithm on a number of inverse problems such as denoising, deblurring, super-resolution, inpainting and devignetting. To the best of our knowledge, FEPLL is the first algorithm that can competitively restore a 512x512 pixel image in under 0.5s for all the degradations mentioned above without specialized code optimizations such as CPU parallelization or GPU implementation.