PyTorchKR Papers

최신 논문

총 3,696편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2306.09839공식 코드 · Papers with Code

Super-Resolution Radar Imaging with Sparse Arrays Using a Deep Neural Network Trained with Enhanced Virtual Data

This paper introduces a method based on a deep neural network (DNN) that is perfectly capable of processing radar data from extremely thinned radar apertures. The proposed DNN processing can provide both aliasing-free radar imaging and super-resolution. The results are validated by measuring the detection performance on realistic simulation data and by evaluating the Point-Spread-function (PSF) and the target-separation performance on measured point-like targets. Also, a qualitative evaluation of a typical automotive scene is conducted. It is shown that this approach can outperform state-of-the-art subspace algorithms and also other existing machine learning solutions. The presented results suggest that machine learning approaches trained with sufficiently sophisticated virtual input data are a very promising alternative to compressed sensing and subspace approaches in radar signal processing. The key to this performance is that the DNN is trained using realistic simulation data that perfectly mimic a given sparse antenna radar array hardware as the input. As ground truth, ultra-high resolution data from an enhanced virtual radar are simulated. Contrary to other work, the DNN utilizes the complete radar cube and not only the antenna channel information at certain range-Doppler detections. After training, the proposed DNN is capable of sidelobe- and ambiguity-free imaging. It simultaneously delivers nearly the same resolution and image quality as would be achieved with a fully occupied array.

arXiv:2306.09807공식 코드 · Papers with Code

FALL-E: A Foley Sound Synthesis Model and Strategies

This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed prompt engineering for quality, coherence, and diversity. FALL-E was evaluated by an objective measure as well as listening tests in the DCASE 2023 challenge Task 7. The submission achieved the second place on average, while achieving the best score for diversity, second place for audio quality, and third place for class fitness.

arXiv:2306.09426공식 코드 · Papers with Code

Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation

Despite several solutions and experiments have been conducted recently addressing image super-resolution (SR), boosted by deep learning (DL) techniques, they do not usually design evaluations with high scaling factors, capping it at 2x or 4x. Moreover, the datasets are generally benchmarks which do not truly encompass significant diversity of domains to proper evaluate the techniques. It is also interesting to remark that blind SR is attractive for real-world scenarios since it is based on the idea that the degradation process is unknown, and hence techniques in this context rely basically on low-resolution (LR) images. In this article, we present a high-scale (8x) controlled experiment which evaluates five recent DL techniques tailored for blind image SR: Adaptive Pseudo Augmentation (APA), Blind Image SR with Spatially Variant Degradations (BlindSR), Deep Alternating Network (DAN), FastGAN, and Mixture of Experts Super-Resolution (MoESR). We consider 14 small datasets from five different broader domains which are: aerial, fauna, flora, medical, and satellite. Another distinctive characteristic of our evaluation is that some of the DL approaches were designed for single-image SR but others not. Two no-reference metrics were selected, being the classical natural image quality evaluator (NIQE) and the recent transformer-based multi-dimension attention network for no-reference image quality assessment (MANIQA) score, to assess the techniques. Overall, MoESR can be regarded as the best solution although the perceptual quality of the created HR images of all the techniques still needs to improve. Supporting code: https://github.com/vsantjr/DL_BlindSR. Datasets: https://www.kaggle.com/datasets/valdivinosantiago/dl-blindsr-datasets.

논문 ID: document/1011544

GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image Superresolution

Superresolution (SR) of remote sensing images aims to restore high-quality information from low-resolution images. Recently, it has witnessed great strides with the rapid development of deep learning (DL) techniques. Despite their good performance, these DL-based models are often ineffective in balancing global and local feature extraction. Moreover, they are usually hindered by the poor image reconstruction capability of the decoder inside their SR models. To cope with this problem, this work proposes a novel global context-driven residual dense network (GCRDN) for satellite image SR based on the encoder and decoder architecture. In particular, the proposed encoder is endowed with nonlocal sparse attention modules incorporated into the residual dense network to learn robust representations from global features. Furthermore, a decoder equipped with back-sampling blocks is devised to fully exploit the feature maps extracted from the encoder. Extensive experimental comparisons based on two multisensor satellite remote sensing datasets confirm that the proposed GCRDN achieves impressive performance in terms of perceptual quality and fidelity.

논문 ID: document/9615068

Pixel-Level Kernel Estimation for Blind Super-Resolution

Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high-resolution (HR) images using predefined blur kernels — all regions of an image undergoing an identical degradation process. Furthermore, based on this assumption, there have been attempts to estimate the blur kernel of a given LR image, since correct kernel priors are known to be helpful in super-resolution. Although it has been known that blur kernels of real images are non-uniform (spatially varying), current kernel estimation algorithms are mostly done at image-level, estimating one kernel per image. These algorithms inevitably become sub-optimal in handling scenarios where an image is degraded non-uniformly. A divide-and-conquer form of approach, dividing an image into several patches for individual kernel estimation and SR can be a simple solution for this matter. Nevertheless, this approach fails in practice. In this paper, we address this issue by pixel-level kernel estimation. The three main components for training a SR framework based on pixel-level kernel estimation are as follows: Kernel Collage — a method for synthesizing non-uniformly degraded LR images, designed considering the coherency of kernels at neighboring regions while abruptly changing at times, the indirect loss — a novel loss for training the kernel estimator, based on the reconstruction loss, and an additional optimization — a scheme to robustify the SR network to minor errors in kernel estimations. Extensive experiments show the superiority of pixel-level kernel estimation in blind SR, surpassing state-of-the-art methods in terms of quantitative and qualitative results.

arXiv:2306.08768

Generalizable One-shot Neural Head Avatar

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. Existing methods either involve time-consuming optimization for a specific person with multiple images, or they struggle to synthesize intricate appearance details beyond the facial region. To address these limitations, we propose a framework that not only generalizes to unseen identities based on a single-view image without requiring person-specific optimization, but also captures characteristic details within and beyond the face area (e.g. hairstyle, accessories, etc.). At the core of our method are three branches that produce three tri-planes representing the coarse 3D geometry, detailed appearance of a source image, as well as the expression of a target image. By applying volumetric rendering to the combination of the three tri-planes followed by a super-resolution module, our method yields a high fidelity image of the desired identity, expression and pose. Once trained, our model enables efficient 3D head avatar reconstruction and animation via a single forward pass through a network. Experiments show that the proposed approach generalizes well to unseen validation datasets, surpassing SOTA baseline methods by a large margin on head avatar reconstruction and animation.

arXiv:2306.07724

Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks

Images cannot always be expected to come in a certain standard format and orientation. Deep networks need to be trained to take into account unexpected variations in orientation or format. For this purpose, training data should be enriched to include different conditions. In this study, the effects of data enrichment on the performance of deep networks in the super resolution problem were investigated experimentally. A total of six basic image transformations were used for the enrichment procedures. In the experiments, two deep network models were trained with variants of the ILSVRC2012 dataset enriched by these six image transformation processes. Considering a single image transformation, it has been observed that the data enriched with 180 degree rotation provides the best results. The most unsuccessful result was obtained when the models were trained on the enriched data generated by the flip upside down process. Models scored highest when trained with a mix of all transformations.

arXiv:2306.07292공식 코드 · Papers with Code

SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation

Open data is frequently released spatially aggregated, usually to comply with privacy policies. But coarse, heterogeneous aggregations complicate learning and integration for downstream AI/ML systems. In this work, we consider models to disaggregate spatio-temporal data from a low-resolution, irregular partition (e.g., census tract) to a high-resolution, irregular partition (e.g., city block). We propose an overarching model named the Structurally-Aware Recurrent Network (SARN), which integrates structurally-aware spatial attention (SASA) layers into the Gated Recurrent Unit (GRU) model. The spatial attention layers capture spatial interactions among regions, while the gated recurrent module captures the temporal dependencies. Each SASA layer calculates both global and structural attention -- global attention facilitates comprehensive interactions between different geographic levels, while structural attention leverages the containment relationship between different geographic levels (e.g., a city block being wholly contained within a census tract) to ensure coherent and consistent results. For scenarios with limited historical training data, we explore transfer learning and show that a model pre-trained on one city variable can be fine-tuned for another city variable using only a few hundred samples. Evaluating these techniques on two mobility datasets, we find that on both datasets, SARN significantly outperforms other neural models (5% and 1%) and typical heuristic methods (40% and 14%), enabling us to generate realistic, high-quality fine-grained data for downstream applications.

arXiv:2306.06669공식 코드 · Papers with Code

TransMRSR: Transformer-based Self-Distilled Generative Prior for Brain MRI Super-Resolution

Magnetic resonance images (MRI) acquired with low through-plane resolution compromise time and cost. The poor resolution in one orientation is insufficient to meet the requirement of high resolution for early diagnosis of brain disease and morphometric study. The common Single image super-resolution (SISR) solutions face two main challenges: (1) local detailed and global anatomical structural information combination; and (2) large-scale restoration when applied for reconstructing thick-slice MRI into high-resolution (HR) iso-tropic data. To address these problems, we propose a novel two-stage network for brain MRI SR named TransMRSR based on the convolutional blocks to extract local information and transformer blocks to capture long-range dependencies. TransMRSR consists of three modules: the shallow local feature extraction, the deep non-local feature capture, and the HR image reconstruction. We perform a generative task to encapsulate diverse priors into a generative network (GAN), which is the decoder sub-module of the deep non-local feature capture part, in the first stage. The pre-trained GAN is used for the second stage of SR task. We further eliminate the potential latent space shift caused by the two-stage training strategy through the self-distilled truncation trick. The extensive experiments show that our method achieves superior performance to other SSIR methods on both public and private datasets. Code is released at https://github.com/goddesshs/TransMRSR.git .

arXiv:2306.06513

Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration

Recent work on discrete generative priors, in the form of codebooks, has shown exciting performance for image reconstruction and restoration, as the discrete prior space spanned by the codebooks increases the robustness against diverse image degradations. Nevertheless, these methods require separate training of codebooks for different image categories, which limits their use to specific image categories only (e.g. face, architecture, etc.), and fail to handle arbitrary natural images. In this paper, we propose AdaCode for learning image-adaptive codebooks for class-agnostic image restoration. Instead of learning a single codebook for each image category, we learn a set of basis codebooks. For a given input image, AdaCode learns a weight map with which we compute a weighted combination of these basis codebooks for adaptive image restoration. Intuitively, AdaCode is a more flexible and expressive discrete generative prior than previous work. Experimental results demonstrate that AdaCode achieves state-of-the-art performance on image reconstruction and restoration tasks, including image super-resolution and inpainting.

arXiv:2306.05907공식 코드 · Papers with Code

2DeteCT -- A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning

Recent research in computational imaging largely focuses on developing machine learning (ML) techniques for image reconstruction, which requires large-scale training datasets consisting of measurement data and ground-truth images. However, suitable experimental datasets for X-ray Computed Tomography (CT) are scarce, and methods are often developed and evaluated only on simulated data. We fill this gap by providing the community with a versatile, open 2D fan-beam CT dataset suitable for developing ML techniques for a range of image reconstruction tasks. To acquire it, we designed a sophisticated, semi-automatic scan procedure that utilizes a highly-flexible laboratory X-ray CT setup. A diverse mix of samples with high natural variability in shape and density was scanned slice-by-slice (5000 slices in total) with high angular and spatial resolution and three different beam characteristics: A high-fidelity, a low-dose and a beam-hardening-inflicted mode. In addition, 750 out-of-distribution slices were scanned with sample and beam variations to accommodate robustness and segmentation tasks. We provide raw projection data, reference reconstructions and segmentations based on an open-source data processing pipeline.

arXiv:2306.05812공식 코드 · Papers with Code

HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection

An individualised head-related transfer function (HRTF) is very important for creating realistic virtual reality (VR) and augmented reality (AR) environments. However, acoustically measuring high-quality HRTFs requires expensive equipment and an acoustic lab setting. To overcome these limitations and to make this measurement more efficient HRTF upsampling has been exploited in the past where a high-resolution HRTF is created from a low-resolution one. This paper demonstrates how generative adversarial networks (GANs) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional super-resolution generative adversarial network (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, spherical harmonic (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of log-spectral distortion (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions).

arXiv:2306.05390공식 코드 · Papers with Code

HQ-50K: A Large-scale, High-quality Dataset for Image Restoration

This paper introduces a new large-scale image restoration dataset, called HQ-50K, which contains 50,000 high-quality images with rich texture details and semantic diversity. We analyze existing image restoration datasets from five different perspectives, including data scale, resolution, compression rates, texture details, and semantic coverage. However, we find that all of these datasets are deficient in some aspects. In contrast, HQ-50K considers all of these five aspects during the data curation process and meets all requirements. We also present a new Degradation-Aware Mixture of Expert (DAMoE) model, which enables a single model to handle multiple corruption types and unknown levels. Our extensive experiments demonstrate that HQ-50K consistently improves the performance on various image restoration tasks, such as super-resolution, denoising, dejpeg, and deraining. Furthermore, our proposed DAMoE, trained on our \dataset, outperforms existing state-of-the-art unified models designed for multiple restoration tasks and levels. The dataset and code are available at \url{https://github.com/littleYaang/HQ-50K}.

arXiv:2306.04469공식 코드 · Papers with Code

Model-Based Deep Learning

Signal processing traditionally relies on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and additional domain knowledge. Simple classical models are useful but sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior. More recently, deep learning approaches that use deep neural networks are becoming increasingly popular. Deep learning systems do not rely on mathematical modeling, and learn their mapping from data, which allows them to operate in complex environments. However, they lack the interpretability and reliability of model-based methods, typically require large training sets to obtain good performance, and tend to be computationally complex. Model-based signal processing methods and data-centric deep learning each have their pros and cons. These paradigms can be characterized as edges of a continuous spectrum varying in specificity and parameterization. The methodologies that lie in the middle ground of this spectrum, thus integrating model-based signal processing with deep learning, are referred to as model-based deep learning, and are the focus here. This monograph provides a tutorial style presentation of model-based deep learning methodologies. These are families of algorithms that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches. Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data. We accompany our presentation with running examples, in super-resolution, dynamic systems, and array processing. We show how they are expressed using the provided characterization and specialized in each of the detailed methodologies.

arXiv:2306.03380

A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions

The existing face image super-resolution (FSR) algorithms usually train a specific model for a specific low input resolution for optimal results. By contrast, we explore in this work a unified framework that is trained once and then used to super-resolve input face images of varied low resolutions. For that purpose, we propose a novel neural network architecture that is composed of three anchor auto-encoders, one feature weight regressor and a final image decoder. The three anchor auto-encoders are meant for optimal FSR for three pre-defined low input resolutions, or named anchor resolutions, respectively. An input face image of an arbitrary low resolution is firstly up-scaled to the target resolution by bi-cubic interpolation and then fed to the three auto-encoders in parallel. The three encoded anchor features are then fused with weights determined by the feature weight regressor. At last, the fused feature is sent to the final image decoder to derive the super-resolution result. As shown by experiments, the proposed algorithm achieves robust and state-of-the-art performance over a wide range of low input resolutions by a single framework. Code and models will be made available after the publication of this work.

arXiv:2306.03110

SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting

Data-driven medium-range weather forecasting has attracted much attention in recent years. However, the forecasting accuracy at high resolution is unsatisfactory currently. Pursuing high-resolution and high-quality weather forecasting, we develop a data-driven model SwinRDM which integrates an improved version of SwinRNN with a diffusion model. SwinRDM performs predictions at 0.25-degree resolution and achieves superior forecasting accuracy to IFS (Integrated Forecast System), the state-of-the-art operational NWP model, on representative atmospheric variables including 500 hPa geopotential (Z500), 850 hPa temperature (T850), 2-m temperature (T2M), and total precipitation (TP), at lead times of up to 5 days. We propose to leverage a two-step strategy to achieve high-resolution predictions at 0.25-degree considering the trade-off between computation memory and forecasting accuracy. Recurrent predictions for future atmospheric fields are firstly performed at 1.40625-degree resolution, and then a diffusion-based super-resolution model is leveraged to recover the high spatial resolution and finer-scale atmospheric details. SwinRDM pushes forward the performance and potential of data-driven models for a large margin towards operational applications.

arXiv:2306.03025

AI Techniques for Cone Beam Computed Tomography in Dentistry: Trends and Practices

Cone-beam computed tomography (CBCT) is a popular imaging modality in dentistry for diagnosing and planning treatment for a variety of oral diseases with the ability to produce detailed, three-dimensional images of the teeth, jawbones, and surrounding structures. CBCT imaging has emerged as an essential diagnostic tool in dentistry. CBCT imaging has seen significant improvements in terms of its diagnostic value, as well as its accuracy and efficiency, with the most recent development of artificial intelligence (AI) techniques. This paper reviews recent AI trends and practices in dental CBCT imaging. AI has been used for lesion detection, malocclusion classification, measurement of buccal bone thickness, and classification and segmentation of teeth, alveolar bones, mandibles, landmarks, contours, and pharyngeal airways using CBCT images. Mainly machine learning algorithms, deep learning algorithms, and super-resolution techniques are used for these tasks. This review focuses on the potential of AI techniques to transform CBCT imaging in dentistry, which would improve both diagnosis and treatment planning. Finally, we discuss the challenges and limitations of artificial intelligence in dentistry and CBCT imaging.

arXiv:2306.02443

ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes

While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on optimizing performance, rather than paying due attention to efficiency - a crucial factor in ensuring deployment of the STISR-STR pipeline. In this work, we propose a novel Efficient Scene Text Image Super-resolution (ESTISR) Network for resource-limited deployment platform. ESTISR's functionality primarily depends on two critical components: a CNN-based feature extractor and an efficient self-attention mechanism used for decoding low-resolution images. We designed a re-parameterized inverted residual block specifically suited for resource-limited circumstances as the feature extractor. Meanwhile, we proposed a novel self-attention mechanism, softmax shrinking, based on a kernel-based approach. This innovative technique offers linear complexity while also naturally incorporating discriminating low-level features into the self-attention structure. Extensive experiments on TextZoom show that ESTISR retains a high image restoration quality and improved STR accuracy of low-resolution images. Furthermore, ESTISR consistently outperforms current methods in terms of actual running time and peak memory consumption, while achieving a better trade-off between performance and efficiency.

arXiv:2306.02398공식 코드 · Papers with Code

Scale Guided Hypernetwork for Blind Super-Resolution Image Quality Assessment

With the emergence of image super-resolution (SR) algorithm, how to blindly evaluate the quality of super-resolution images has become an urgent task. However, existing blind SR image quality assessment (IQA) metrics merely focus on visual characteristics of super-resolution images, ignoring the available scale information. In this paper, we reveal that the scale factor has a statistically significant impact on subjective quality scores of SR images, indicating that the scale information can be used to guide the task of blind SR IQA. Motivated by this, we propose a scale guided hypernetwork framework that evaluates SR image quality in a scale-adaptive manner. Specifically, the blind SR IQA procedure is divided into three stages, i.e., content perception, evaluation rule generation, and quality prediction. After content perception, a hypernetwork generates the evaluation rule used in quality prediction based on the scale factor of the SR image. We apply the proposed scale guided hypernetwork framework to existing representative blind IQA metrics, and experimental results show that the proposed framework not only boosts the performance of these IQA metrics but also enhances their generalization abilities. Source code will be available at https://github.com/JunFu1995/SGH.

arXiv:2306.02277

EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection

In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks. They usually contain limited visual clues and make small faces less distinguishable from the other small objects, which poses great challenge to accurate face detection. Although deep convolutional neural network has significantly promoted the research on face detection recently, current deep face detectors rarely take into account low-resolution faces and are still vulnerable to the real-world scenarios where massive amount of low-resolution faces exist. Consequently, they usually achieve degraded performance for low-resolution face detection. In order to alleviate this problem, we develop an efficient detector termed EfficientSRFace by introducing a feature-level super-resolution reconstruction network for enhancing the feature representation capability of the model. This module plays an auxiliary role in the training process, and can be removed during the inference without increasing the inference time. Extensive experiments on public benchmarking datasets, such as FDDB and WIDER Face, show that the embedded image super-resolution module can significantly improve the detection accuracy at the cost of a small amount of additional parameters and computational overhead, while helping our model achieve competitive performance compared with the state-of-the-arts methods.