PyTorchKR Papers

최신 논문

총 3,696편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

논문 ID: document/9203860

Local-Global Fusion Network for Video Super-Resolution

The goal of video super-resolution technique is to address the problem of effectively restoring high-resolution (HR) videos from low-resolution (LR) ones. Previous methods commonly used optical flow to perform frame alignment and designed a framework from the perspective of space and time. However, inaccurate optical flow estimation may occur easily which leads to inferior restoration effects. In addition, how to effectively fuse the features of various video frames remains a challenging problem. In this paper, we propose a Local-Global Fusion Network (LGFN) to solve the above issues from a novel viewpoint. As an alternative to optical flow, deformable convolutions (DCs) with decreased multi-dilation convolution units (DMDCUs) are applied for efficient implicit alignment. Moreover, a structure with two branches, consisting of a Local Fusion Module (LFM) and a Global Fusion Module (GFM), is proposed to combine information from two different aspects. Specifically, LFM focuses on the relationship between adjacent frames and maintains the temporal consistency while GFM attempts to take advantage of all related features globally with a video shuffle strategy. Benefiting from our advanced network, experimental results on several datasets demonstrate that our LGFN can not only achieve comparative performance with state-of-the-art methods but also possess reliable ability on restoring a variety of video frames. The results on benchmark datasets of our LGFN are presented on https://github.com/BIOINSu/LGFN and the source code will be released as soon as the paper is accepted.

논문 ID: document/9150628

Real-World Super-Resolution via Kernel Estimation and Noise Injection

Recent state-of-the-art super-resolution methods have achieved impressive performance on ideal datasets regardless of blur and noise. However, these methods always fail in real-world image super-resolution, since most of them adopt simple bicubic downsampling from high-quality images to construct Low-Resolution (LR) and High-Resolution (HR) pairs for training which may lose track of frequency-related details. To address this issue, we focus on designing a novel degradation framework for real- world images by estimating various blur kernels as well as real noise distributions. Based on our novel degradation framework, we can acquire LR images sharing a common domain with real-world images. Then, we propose a real- world super-resolution model aiming at better perception. Extensive experiments on synthetic noise data and real- world images demonstrate that our method outperforms the state-of-the-art methods, resulting in lower noise and better visual quality. In addition, our method is the winner of NTIRE 2020 Challenge on both tracks of Real-World Super-Resolution, which significantly outperforms other competitors by large margins.

arXiv:2107.12679

MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN

Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory consumption of GAN-based SR (usually generators) causes performance degradation and more energy consumption, hindering the deployment of GAN-based SR into resource-constricted mobile devices. In this paper, we propose a novel compression framework \textbf{M}ulti-scale \textbf{F}eature \textbf{A}ggregation Net based \textbf{GAN} (MFAGAN) for reducing the memory access cost of the generator. First, to overcome the memory explosion of dense connections, we utilize a memory-efficient multi-scale feature aggregation net as the generator. Second, for faster and more stable training, our method introduces the PatchGAN discriminator. Third, to balance the student discriminator and the compressed generator, we distill both the generator and the discriminator. Finally, we perform a hardware-aware neural architecture search (NAS) to find a specialized SubGenerator for the target mobile phone. Benefiting from these improvements, the proposed MFAGAN achieves up to \textbf{8.3}$\times$ memory saving and \textbf{42.9}$\times$ computation reduction, with only minor visual quality degradation, compared with ESRGAN. Empirical studies also show $\sim$\textbf{70} milliseconds latency on Qualcomm Snapdragon 865 chipset.

arXiv:2107.12541

BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation

Depth map super-resolution is a task with high practical application requirements in the industry. Existing color-guided depth map super-resolution methods usually necessitate an extra branch to extract high-frequency detail information from RGB image to guide the low-resolution depth map reconstruction. However, because there are still some differences between the two modalities, direct information transmission in the feature dimension or edge map dimension cannot achieve satisfactory result, and may even trigger texture copying in areas where the structures of the RGB-D pair are inconsistent. Inspired by the multi-task learning, we propose a joint learning network of depth map super-resolution (DSR) and monocular depth estimation (MDE) without introducing additional supervision labels. For the interaction of two subnetworks, we adopt a differentiated guidance strategy and design two bridges correspondingly. One is the high-frequency attention bridge (HABdg) designed for the feature encoding process, which learns the high-frequency information of the MDE task to guide the DSR task. The other is the content guidance bridge (CGBdg) designed for the depth map reconstruction process, which provides the content guidance learned from DSR task for MDE task. The entire network architecture is highly portable and can provide a paradigm for associating the DSR and MDE tasks. Extensive experiments on benchmark datasets demonstrate that our method achieves competitive performance. Our code and models are available at https://rmcong.github.io/proj_BridgeNet.html.

arXiv:2107.11639공식 코드 · Papers with Code

Self-Conditioned Probabilistic Learning of Video Rescaling

Bicubic downscaling is a prevalent technique used to reduce the video storage burden or to accelerate the downstream processing speed. However, the inverse upscaling step is non-trivial, and the downscaled video may also deteriorate the performance of downstream tasks. In this paper, we propose a self-conditioned probabilistic framework for video rescaling to learn the paired downscaling and upscaling procedures simultaneously. During the training, we decrease the entropy of the information lost in the downscaling by maximizing its probability conditioned on the strong spatial-temporal prior information within the downscaled video. After optimization, the downscaled video by our framework preserves more meaningful information, which is beneficial for both the upscaling step and the downstream tasks, e.g., video action recognition task. We further extend the framework to a lossy video compression system, in which a gradient estimator for non-differential industrial lossy codecs is proposed for the end-to-end training of the whole system. Extensive experimental results demonstrate the superiority of our approach on video rescaling, video compression, and efficient action recognition tasks.

arXiv:2107.11617

LAConv: Local Adaptive Convolution for Image Fusion

The convolution operation is a powerful tool for feature extraction and plays a prominent role in the field of computer vision. However, when targeting the pixel-wise tasks like image fusion, it would not fully perceive the particularity of each pixel in the image if the uniform convolution kernel is used on different patches. In this paper, we propose a local adaptive convolution (LAConv), which is dynamically adjusted to different spatial locations. LAConv enables the network to pay attention to every specific local area in the learning process. Besides, the dynamic bias (DYB) is introduced to provide more possibilities for the depiction of features and make the network more flexible. We further design a residual structure network equipped with the proposed LAConv and DYB modules, and apply it to two image fusion tasks. Experiments for pansharpening and hyperspectral image super-resolution (HISR) demonstrate the superiority of our method over other state-of-the-art methods. It is worth mentioning that LAConv can also be competent for other super-resolution tasks with less computation effort.

arXiv:2107.11263

Compressed Ultrasound Imaging:from Sub-Nyquist Rates to Super-Resolution

The multi-billion dollar, worldwide medical ultrasound (US) market continues to grow annually. Its non-ionizing nature, real-time capabilities and relatively low cost, compared to other imaging modalities, have led to significant applications in many different fields, including cardiology, angiology, obstetrics and emergency medicine. Facilitated by ongoing innovations, US continues to change rules and norms regarding patient screening, diagnosis and surgery. This huge and promising market is constantly driven by new imaging and processing techniques. From 3D images to sophisticated software, hardware and portability improvements, it is clear that the status of US as one of the leading medical imaging technologies is ensured for many years ahead. However, as imaging systems evolve, new engineering challenges emerge. Acquisition, transmission and processing of huge amounts of data are common for all ultrasound-based imaging modalities. Moreover, achieving higher resolution is constantly on demand, as improved diagnosis could be achieved by better visualization of organs and blood vessels deep within tissues. In this article, our goal is to motivate further interest and research in emerging processing techniques, as well as their applications in medical ultrasound, enabled by recent advancements in signal processing algorithms and deep learning. We address some of the primary challenges and potential remedies from a signal processing perspective, by exploiting the inherent structure of the received US signal.

arXiv:2107.10833공식 코드 · Papers with Code

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images. In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data. Specifically, a high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process. In addition, we employ a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics. Extensive comparisons have shown its superior visual performance than prior works on various real datasets. We also provide efficient implementations to synthesize training pairs on the fly.

arXiv:2107.09989

High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss

Magnetic resonance imaging (MRI) is an important medical imaging modality, but its acquisition speed is quite slow due to the physiological limitations. Recently, super-resolution methods have shown excellent performance in accelerating MRI. In some circumstances, it is difficult to obtain high-resolution images even with prolonged scan time. Therefore, we proposed a novel super-resolution method that uses a generative adversarial network (GAN) with cyclic loss and attention mechanism to generate high-resolution MR images from low-resolution MR images by a factor of 2. We implemented our model on pelvic images from healthy subjects as training and validation data, while those data from patients were used for testing. The MR dataset was obtained using different imaging sequences, including T2, T2W SPAIR, and mDIXON-W. Four methods, i.e., BICUBIC, SRCNN, SRGAN, and EDSR were used for comparison. Structural similarity, peak signal to noise ratio, root mean square error, and variance inflation factor were used as calculation indicators to evaluate the performances of the proposed method. Various experimental results showed that our method can better restore the details of the high-resolution MR image as compared to the other methods. In addition, the reconstructed high-resolution MR image can provide better lesion textures in the tumor patients, which is promising to be used in clinical diagnosis.

arXiv:2107.09523

ProfileSR-GAN: A GAN based Super-Resolution Method for Generating High-Resolution Load Profiles

It is a common practice for utilities to down-sample smart meter measurements from high resolution (e.g. 1-min or 1-sec) to low resolution (e.g. 15-, 30- or 60-min) to lower the data transmission and storage cost. However, down-sampling can remove high-frequency components from time-series load profiles, making them unsuitable for in-depth studies such as quasi-static power flow analysis or non-intrusive load monitoring (NILM). Thus, in this paper, we propose ProfileSR-GAN: a Generative Adversarial Network (GAN) based load profile super-resolution (LPSR) framework for restoring high-frequency components lost through the smoothing effect of the down-sampling process. The LPSR problem is formulated as a Maximum-a-Prior problem. When training the ProfileSR-GAN generator network, to make the generated profiles more realistic, we introduce two new shape-related losses in addition to conventionally used content loss: adversarial loss and feature-matching loss. Moreover, a new set of shape-based evaluation metrics are proposed to evaluate the realisticness of the generated profiles. Simulation results show that ProfileSR-GAN outperforms Mean-Square Loss based methods in all shape-based metrics. The successful application in NILM further demonstrates that ProfileSR-GAN is effective in recovering high-resolution realistic waveforms.

arXiv:2107.09427

RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of different perceptual metrics. Specifically, we first train a Ranker which can learn the behaviour of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality. The most appealing part is that the proposed method can combine the strengths of different SR methods to generate better results. Furthermore, we extend our method to multiple Rankers to provide multi-dimension constraints for the generator. Extensive experiments show that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics and quality. Project page: https://wenlongzhang0517.github.io/Projects/RankSRGAN

arXiv:2107.08717

Joint Implicit Image Function for Guided Depth Super-Resolution

Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually view this task as a generalized guided filtering problem that relies on designing explicit filters and objective functions, or a dense regression problem that directly predicts the target image via deep neural networks. These methods suffer from either model capability or interpretability. Inspired by the recent progress in implicit neural representation, we propose to formulate the guided super-resolution as a neural implicit image interpolation problem, where we take the form of a general image interpolation but use a novel Joint Implicit Image Function (JIIF) representation to learn both the interpolation weights and values. JIIF represents the target image domain with spatially distributed local latent codes extracted from the input image and the guide image, and uses a graph attention mechanism to learn the interpolation weights at the same time in one unified deep implicit function. We demonstrate the effectiveness of our JIIF representation on guided depth super-resolution task, significantly outperforming state-of-the-art methods on three public benchmarks. Code can be found at \url{https://git.io/JC2sU}.

arXiv:2107.07975

Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation

Optimising the analysis of cardiac structure and function requires accurate 3D representations of shape and motion. However, techniques such as cardiac magnetic resonance imaging are conventionally limited to acquiring contiguous cross-sectional slices with low through-plane resolution and potential inter-slice spatial misalignment. Super-resolution in medical imaging aims to increase the resolution of images but is conventionally trained on features from low resolution datasets and does not super-resolve corresponding segmentations. Here we propose a semi-supervised multi-task generative adversarial network (Gemini-GAN) that performs joint super-resolution of the images and their labels using a ground truth of high resolution 3D cines and segmentations, while an unsupervised variational adversarial mixture autoencoder (V-AMA) is used for continuous domain adaptation. Our proposed approach is extensively evaluated on two transnational multi-ethnic populations of 1,331 and 205 adults respectively, delivering an improvement on state of the art methods in terms of Dice index, peak signal to noise ratio, and structural similarity index measure. This framework also exceeds the performance of state of the art generative domain adaptation models on external validation (Dice index 0.81 vs 0.74 for the left ventricle). This demonstrates how joint super-resolution and segmentation, trained on 3D ground-truth data with cross-domain generalization, enables robust precision phenotyping in diverse populations.

arXiv:2107.07397

Level generation and style enhancement -- deep learning for game development overview

We present practical approaches of using deep learning to create and enhance level maps and textures for video games -- desktop, mobile, and web. We aim to present new possibilities for game developers and level artists. The task of designing levels and filling them with details is challenging. It is both time-consuming and takes effort to make levels rich, complex, and with a feeling of being natural. Fortunately, recent progress in deep learning provides new tools to accompany level designers and visual artists. Moreover, they offer a way to generate infinite worlds for game replayability and adjust educational games to players' needs. We present seven approaches to create level maps, each using statistical methods, machine learning, or deep learning. In particular, we include: - Generative Adversarial Networks for creating new images from existing examples (e.g. ProGAN). - Super-resolution techniques for upscaling images while preserving crisp detail (e.g. ESRGAN). - Neural style transfer for changing visual themes. - Image translation - turning semantic maps into images (e.g. GauGAN). - Semantic segmentation for turning images into semantic masks (e.g. U-Net). - Unsupervised semantic segmentation for extracting semantic features (e.g. Tile2Vec). - Texture synthesis - creating large patterns based on a smaller sample (e.g. InGAN).

arXiv:2107.06536

Multi-Attention Generative Adversarial Network for Remote Sensing Image Super-Resolution

Image super-resolution (SR) methods can generate remote sensing images with high spatial resolution without increasing the cost, thereby providing a feasible way to acquire high-resolution remote sensing images, which are difficult to obtain due to the high cost of acquisition equipment and complex weather. Clearly, image super-resolution is a severe ill-posed problem. Fortunately, with the development of deep learning, the powerful fitting ability of deep neural networks has solved this problem to some extent. In this paper, we propose a network based on the generative adversarial network (GAN) to generate high resolution remote sensing images, named the multi-attention generative adversarial network (MA-GAN). We first designed a GAN-based framework for the image SR task. The core to accomplishing the SR task is the image generator with post-upsampling that we designed. The main body of the generator contains two blocks; one is the pyramidal convolution in the residual-dense block (PCRDB), and the other is the attention-based upsample (AUP) block. The attentioned pyramidal convolution (AttPConv) in the PCRDB block is a module that combines multi-scale convolution and channel attention to automatically learn and adjust the scaling of the residuals for better results. The AUP block is a module that combines pixel attention (PA) to perform arbitrary multiples of upsampling. These two blocks work together to help generate better quality images. For the loss function, we design a loss function based on pixel loss and introduce both adversarial loss and feature loss to guide the generator learning. We have compared our method with several state-of-the-art methods on a remote sensing scene image dataset, and the experimental results consistently demonstrate the effectiveness of the proposed MA-GAN.

arXiv:2107.05930

Single-shot structured illumination microscopy

Structured illumination microscopy (SIM) can double the resolution beyond the light diffraction limit, but it comes at the cost of multiple camera exposures and the heavy computation burden of multiple Fourier transforms. In this paper, we report a novel technique termed single-shot SIM, to overcome these limitations. A multi-task joint deep-learning strategy is proposed. Generative adversative networks (GAN) are employed to generate five structured illumination images based on the single-shot structured illumination image. U-Net is employed to reconstruct the super-resolution image from these six generated images without time-consuming Fourier transform. By imaging a self-assembling DNB array, we experimentally verified that this technique could perform single-shot super-resolution reconstruction comparing favorably with conventional SIM. This single-shot SIM technique may ultimately overcome the limitations of multiple exposures and Fourier transforms and is potentially applied for high-throughput gene sequencing.

arXiv:2107.05270

Learned super resolution ultrasound for improved breast lesion characterization

Breast cancer is the most common malignancy in women. Mammographic findings such as microcalcifications and masses, as well as morphologic features of masses in sonographic scans, are the main diagnostic targets for tumor detection. However, improved specificity of these imaging modalities is required. A leading alternative target is neoangiogenesis. When pathological, it contributes to the development of numerous types of tumors, and the formation of metastases. Hence, demonstrating neoangiogenesis by visualization of the microvasculature may be of great importance. Super resolution ultrasound localization microscopy enables imaging of the microvasculature at the capillary level. Yet, challenges such as long reconstruction time, dependency on prior knowledge of the system Point Spread Function (PSF), and separability of the Ultrasound Contrast Agents (UCAs), need to be addressed for translation of super-resolution US into the clinic. In this work we use a deep neural network architecture that makes effective use of signal structure to address these challenges. We present in vivo human results of three different breast lesions acquired with a clinical US scanner. By leveraging our trained network, the microvasculature structure is recovered in a short time, without prior PSF knowledge, and without requiring separability of the UCAs. Each of the recoveries exhibits a different structure that corresponds with the known histological structure. This study demonstrates the feasibility of in vivo human super resolution, based on a clinical scanner, to increase US specificity for different breast lesions and promotes the use of US in the diagnosis of breast pathologies.

arXiv:2107.05307공식 코드 · Papers with Code

Real-Time Super-Resolution System of 4K-Video Based on Deep Learning

Video super-resolution (VSR) technology excels in reconstructing low-quality video, avoiding unpleasant blur effect caused by interpolation-based algorithms. However, vast computation complexity and memory occupation hampers the edge of deplorability and the runtime inference in real-life applications, especially for large-scale VSR task. This paper explores the possibility of real-time VSR system and designs an efficient and generic VSR network, termed EGVSR. The proposed EGVSR is based on spatio-temporal adversarial learning for temporal coherence. In order to pursue faster VSR processing ability up to 4K resolution, this paper tries to choose lightweight network structure and efficient upsampling method to reduce the computation required by EGVSR network under the guarantee of high visual quality. Besides, we implement the batch normalization computation fusion, convolutional acceleration algorithm and other neural network acceleration techniques on the actual hardware platform to optimize the inference process of EGVSR network. Finally, our EGVSR achieves the real-time processing capacity of [email omitted]. Compared with TecoGAN, the most advanced VSR network at present, we achieve 85.04% reduction of computation density and 7.92x performance speedups. In terms of visual quality, the proposed EGVSR tops the list of most metrics (such as LPIPS, tOF, tLP, etc.) on the public test dataset Vid4 and surpasses other state-of-the-art methods in overall performance score. The source code of this project can be found on https://github.com/Thmen/EGVSR.

arXiv:2107.04133

Effectiveness of State-of-the-Art Super Resolution Algorithms in Surveillance Environment

Image Super Resolution (SR) finds applications in areas where images need to be closely inspected by the observer to extract enhanced information. One such focused application is an offline forensic analysis of surveillance feeds. Due to the limitations of camera hardware, camera pose, limited bandwidth, varying illumination conditions, and occlusions, the quality of the surveillance feed is significantly degraded at times, thereby compromising monitoring of behavior, activities, and other sporadic information in the scene. For the proposed research work, we have inspected the effectiveness of four conventional yet effective SR algorithms and three deep learning-based SR algorithms to seek the finest method that executes well in a surveillance environment with limited training data op-tions. These algorithms generate an enhanced resolution output image from a sin-gle low-resolution (LR) input image. For performance analysis, a subset of 220 images from six surveillance datasets has been used, consisting of individuals with varying distances from the camera, changing illumination conditions, and complex backgrounds. The performance of these algorithms has been evaluated and compared using both qualitative and quantitative metrics. These SR algo-rithms have also been compared based on face detection accuracy. By analyzing and comparing the performance of all the algorithms, a Convolutional Neural Network (CNN) based SR technique using an external dictionary proved to be best by achieving robust face detection accuracy and scoring optimal quantitative metric results under different surveillance conditions. This is because the CNN layers progressively learn more complex features using an external dictionary.

arXiv:2107.03887

Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation

In cardiac magnetic resonance (CMR) imaging, a 3D high-resolution segmentation of the heart is essential for detailed description of its anatomical structures. However, due to the limit of acquisition duration and respiratory/cardiac motion, stacks of multi-slice 2D images are acquired in clinical routine. The segmentation of these images provides a low-resolution representation of cardiac anatomy, which may contain artefacts caused by motion. Here we propose a novel latent optimisation framework that jointly performs motion correction and super resolution for cardiac image segmentations. Given a low-resolution segmentation as input, the framework accounts for inter-slice motion in cardiac MR imaging and super-resolves the input into a high-resolution segmentation consistent with input. A multi-view loss is incorporated to leverage information from both short-axis view and long-axis view of cardiac imaging. To solve the inverse problem, iterative optimisation is performed in a latent space, which ensures the anatomical plausibility. This alleviates the need of paired low-resolution and high-resolution images for supervised learning. Experiments on two cardiac MR datasets show that the proposed framework achieves high performance, comparable to state-of-the-art super-resolution approaches and with better cross-domain generalisability and anatomical plausibility.